messages
listlengths 3
3
| videos
listlengths 1
1
| label
stringclasses 2
values | qid
stringlengths 16
21
| query
stringlengths 31
489
| pos_video_id
stringlengths 13
13
| pos_index
int64 -1
9.89k
| neg_video_id
stringlengths 0
13
| neg_index
int64 -1
9.89k
| neg_rank
int64 0
5
| neg_caption
stringlengths 31
468
⌀ |
|---|---|---|---|---|---|---|---|---|---|---|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_jsxrJJkUl2E.mp4"
] |
pos
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man in a black jacket, but it is missing the specific context of a man holding a sandwich in front of a brick building with a sloped roof, as well as the detail of another person lying on the ground in distress. Query Rewrite: A man in a black jacket and blue shorts stands in front of a brick building with a sloped roof, holding a sandwich, while another person lies on the ground in distress.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_JNFUZz1bqmg.mp4"
] |
neg
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
|
v_JNFUZz1bqmg
| 1,540
| 1
|
Two men, one wearing a black jacket and blue jeans, and the other wearing a gray jacket, are kneeling on the ground in an outdoor setting with a paved area and a building in the background. The man in gray is possibly receiving assistance from the man in black.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of individuals interacting on the ground, but it is missing the specific details of a man in a black jacket and blue shorts holding a sandwich in front of a brick building with a sloped roof, as another person lies in distress nearby. Query Rewrite: A man in a black jacket and blue shorts stands in front of a brick building with a sloped roof, holding a sandwich, while another person lies on the ground in distress.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_Is0_Qv6NLm0.mp4"
] |
neg
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
|
v_Is0_Qv6NLm0
| 4,266
| 2
|
Men in casual attire converse with a homeless youth, who is sitting on the ground with a sign and a cup, on a city sidewalk with heavy foot traffic and numerous advertisements.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man, but it is missing the specific context of a man in a black jacket and blue shorts holding a sandwich in front of a brick building with a sloped roof, as another person lies on the ground in distress. Query Rewrite: A man in a black jacket and blue shorts stands in front of a brick building with a sloped roof, holding a sandwich, while another person lies on the ground in distress.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_gpmrwsV9skQ.mp4"
] |
neg
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
|
v_gpmrwsV9skQ
| 3,540
| 3
|
A man in a suit, on stilts, reads the newspaper while walking and playing piano.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man interacting with another person, but it is missing the specific setting of a brick building, the man's attire of a black jacket and blue shorts, the action of holding a sandwich, and the detail of another person lying on the ground in distress. Query Rewrite: A man in a black jacket and blue shorts stands in front of a brick building with a sloped roof, holding a sandwich, while another person lies on the ground in distress.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_6EKVtCJ2nrs.mp4"
] |
neg
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
|
v_6EKVtCJ2nrs
| 2,109
| 4
|
Amidst a snowy cityscape, a man holds his friend tightly on a rooftop edge, as another looks on.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of men in a public setting, but it is missing the specific details of a man in a black jacket and blue shorts holding a sandwich in front of a brick building with a sloped roof, as another person lies on the ground in distress. Query Rewrite: A man wearing a black jacket and blue shorts stands in front of a brick building with a sloped roof, holding a sandwich, while another person lies on the ground in distress.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_WmQC309JCAI.mkv"
] |
neg
|
1714394113.712092_fig
|
A man is featured in replays, standing in front of a brick building with a sloped roof, wearing a black jacket and blue shorts, holding a sandwich, as another person lies on the ground in distress.
|
v_jsxrJJkUl2E
| 2,990
|
v_WmQC309JCAI
| 4,092
| 5
|
Men in jerseys stand around with crossed arms amidst town square activities.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_dVLIfsEMD8Y.mp4"
] |
pos
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man throwing darts, but it is missing the specific detail of the dartboard being mounted on a beige wall and the presence of a green board to the left. Query Rewrite: A man achieves a bullseye hit on a dartboard mounted on a beige wall, with a green board to the left, while holding a dart in hand.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_rAL6jEy54Tk.mp4"
] |
neg
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
|
v_rAL6jEy54Tk
| 1,639
| 1
|
A man wearing a green cap and brown shirt is depicted in a room with a wooden floor and white wall, engaged in throwing darts at a black dartboard with a bullseye, displaying two darts, one in the bullseye and the other in the outer ring.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man throwing a dart at a dartboard, but it is missing the specific details of the beige wall, the green board to the left, and the context of achieving a bullseye hit with only one dart in hand. Query Rewrite: A man achieves a bullseye hit on a dartboard mounted on a beige wall, holding a dart in hand, with a green board to the left and surrounded by numbered rings.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_aM9WZ1_8yC0.mp4"
] |
neg
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
|
v_aM9WZ1_8yC0
| 8,713
| 2
|
A man in a room with a tiled wall throws a green dart at a dartboard with a bullseye, wearing a brown shirt and a mustache, with two darts already in the bullseye and one in the outer ring.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a dartboard, but it is missing the specific details of a man achieving a bullseye hit on a dartboard mounted on a beige wall with a green board to the left, surrounded by numbered rings. Query Rewrite: A man achieves a bullseye hit on a dartboard mounted on a beige wall, with a green board to the left and surrounded by numbered rings.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_MRpg1K7YWSE.mp4"
] |
neg
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
|
v_MRpg1K7YWSE
| 9,844
| 3
|
A person throws darts at a dartboard with orange and black colors, the background is a wall with a painting of a truck.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man and a dartboard, but it is missing the specific detail of the man achieving a bullseye hit and the description of the beige wall and green board to the left. Query Rewrite: A man achieves a bullseye hit on a dartboard mounted on a beige wall, with a green board to the left and surrounded by numbered rings.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_yJezvcXU4YE.mp4"
] |
neg
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
|
v_yJezvcXU4YE
| 6,073
| 4
|
In the image, a man dressed in a blue and white checkered shirt is depicted as he removes a dart from a classic dartboard, featuring red and black segments.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a successful dart throw hitting the bullseye, but it is missing the specific details of the beige wall, the green board to the left, and the numbered rings surrounding the dartboard. Query Rewrite: A man achieves a bullseye hit with a dart on a dartboard mounted on a beige wall, with a green board to the left and surrounded by numbered rings.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_fpWOf1DR1oA.mp4"
] |
neg
|
1714394113.74587_fig
|
A man, holding a dart in hand, achieves a bullseye hit on the dartboard, mounted on a beige wall with a green board to the left, surrounded by numbered rings.
|
v_dVLIfsEMD8Y
| 3,100
|
v_fpWOf1DR1oA
| 164
| 5
|
A successful throw results in a red dart hitting the bullseye on a standard dartboard with a black background and orange and white scoring lines, mounted on a white wall.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_x08PpU3uQ6Y.mp4"
] |
pos
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman kneeling by a grassy area, but it is missing the white shirt, the large plastic bag, and the body of water nearby that are key elements in the intended scene. Query Rewrite: A woman in a white shirt kneels next to a large plastic bag on the ground in a grassy area near a lake.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_nQgmUkyblgc.mp4"
] |
neg
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
|
v_nQgmUkyblgc
| 9,219
| 1
|
Kneeling by a grassy bank, a woman in purple washes dishes in a wooden platform's shade, her hands scrubbing methodically.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman near water, but it is missing the white shirt, the grassy area, the act of kneeling, and the large plastic bag on the ground. Query Rewrite: A woman in a white shirt kneels next to a large plastic bag on the grass near a lake.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_ZXEc0cahpuw.mp4"
] |
neg
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
|
v_ZXEc0cahpuw
| 8,389
| 2
|
Crouching by the river, a woman in red t-shirt and blue shorts scrubs clothes against a rock.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman in an outdoor setting, but it is missing the specific details of her wearing a white shirt, kneeling next to a large plastic bag, and being near a body of water, which are key elements of the intended scene. Query Rewrite: A woman in a white shirt kneels next to a large plastic bag on the ground in a grassy area near a body of water, possibly a lake.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_w1qa9NOiFbE.mp4"
] |
neg
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
|
v_w1qa9NOiFbE
| 8,984
| 3
|
A woman in a dark-colored outfit washes items by a metal container in the rain, surrounded by other individuals in casual clothing, standing at various distances and observing her actions, in an outdoor setting with a wet and muddy ground.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman in a white shirt and an outdoor setting, but it is missing the specific actions of kneeling down next to a large plastic bag and the context of being near a body of water, possibly a lake. Query Rewrite: A woman in a white shirt kneels down next to a large plastic bag in a grassy area near a body of water, possibly a lake.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_AG2g8djPKV0.mp4"
] |
neg
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
|
v_AG2g8djPKV0
| 402
| 4
|
A woman in a white shirt performs household chores in a natural environment, washing clothes by pouring water from a blue bucket onto them.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the woman wearing a white shirt and kneeling, but it is missing the grassy area, the body of water, and the large plastic bag on the ground. Query Rewrite: A woman in a white shirt is kneeling next to a large plastic bag on the ground in a grassy area near a lake.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_IOoj4yWCoPg.mp4"
] |
neg
|
1714394113.700423_fig
|
A woman in a white shirt is shown standing in a grassy area near a body of water, possibly a lake, and then kneels down next to a large plastic bag on the ground.
|
v_x08PpU3uQ6Y
| 8,267
|
v_IOoj4yWCoPg
| 3,609
| 5
|
A woman wearing a white shirt kneels next to a water hose and a large tub, inserting the hose into the tub as she prepares for laundry or other water-related tasks in an outdoor setting.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A man facilitates blindfolded kids' turns at a pinata game.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_rC24UspQv14.mp4"
] |
pos
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a pinata and the use of a bat, but it is missing the element of blindfolded kids taking turns, as well as the man facilitating their participation in the game. Query Rewrite: A man facilitates the turns of blindfolded kids as they take swings at a pinata during a game.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_4CTczKzaPa4.mp4"
] |
neg
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
|
v_4CTczKzaPa4
| 3,771
| 1
|
A man is blindfolded and swings a bat at a colorful pinata during a celebration or party, with onlookers gathered around a table and chairs in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a pinata game and children, but it is missing the specific detail of blindfolded kids taking turns facilitated by a man. Query Rewrite: A man facilitates a game where blindfolded children take turns hitting a pinata.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_r1ZhBGLfRWY.mp4"
] |
neg
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
|
v_r1ZhBGLfRWY
| 9,324
| 2
|
A boy in a red shirt and camouflage pants is twirled around by a girl in a backyard setting, preparing to break a pinata with a group of children and adults present, including a girl in a striped shirt watching.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a pinata and kids, but it is missing the element of blindfolded children taking turns facilitated by a man. Query Rewrite: A man facilitates turns for blindfolded kids at a pinata game.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_DRI64Xoxy5w.mp4"
] |
neg
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
|
v_DRI64Xoxy5w
| 6,673
| 3
|
A pinata party moment: a boy strikes the pinata, a woman distributes bags to excited kids.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a pinata and blindfolded children, but it is missing the key element of a man facilitating the turns of the kids at the game. Query Rewrite: A man facilitates the turns of blindfolded kids as they take swings at a pinata game.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_jqW7r60gOzE.mp4"
] |
neg
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
|
v_jqW7r60gOzE
| 9,649
| 4
|
A blindfolded boy takes multiple swings at a pinata in a home setting, surrounded by children in dark clothing, with bookshelves in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man facilitates blindfolded kids' turns at a pinata game.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of blindfolded kids and a pinata, but it is missing the element of a man facilitating the turns of the kids at the game. Query Rewrite: A man facilitates the turns of blindfolded kids as they take turns hitting a pinata.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_T98RJsOiQWc.mp4"
] |
neg
|
1714394113.727456_fig
|
A man facilitates blindfolded kids' turns at a pinata game.
|
v_rC24UspQv14
| 6,004
|
v_T98RJsOiQWc
| 4,072
| 5
|
A girl is blindfolded and spun while another prepares to hit a pinata, a man films.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_1FMjfLRpXwM.mp4"
] |
pos
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of hairstyling activity, but it is missing the specific action of spraying hairspray on dark hair and the visibility of the 'JOICO' brand on a plain white wall. Query Rewrite: A hairstylist sprays hairspray on a model's dark hair in front of a plain white wall displaying the 'JOICO' brand.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_QDjaaUtepHo.mp4"
] |
neg
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
|
v_QDjaaUtepHo
| 8,359
| 1
|
The man dries and applies product to the woman's hair with a round brush and his hands.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a stylist and a model, but it is missing the specific action of spraying hairspray, the model's dark hair, and the visible 'JOICO' brand on a plain white wall. Query Rewrite: A hairstylist sprays hairspray on a model's dark hair in front of a plain white wall displaying the 'JOICO' brand.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_WXMb7XF6k8o.mp4"
] |
neg
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
|
v_WXMb7XF6k8o
| 8,039
| 2
|
A stylist, wearing a black V-neck T-shirt and holding a hair product, stands beside a girl with long brown hair, in a salon with a plain, light-colored background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both being set in a salon environment, but it is missing the hairstylist spraying hairspray on a model's dark hair and the visible 'JOICO' brand on a plain white wall. Query Rewrite: A hairstylist sprays hairspray on a model's dark hair in front of a plain white wall with the 'JOICO' brand visible.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_lHy_OZ8GygM.mp4"
] |
neg
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
|
v_lHy_OZ8GygM
| 1,982
| 3
|
In the salon, the woman dries and brushes the man's hair for a polished look.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a hairstylist spraying a hair product, but it is missing the specific details of the model's dark hair and the visible 'JOICO' brand on a plain white wall. Query Rewrite: A hairstylist sprays hairspray on a model's dark hair in front of a plain white wall that prominently displays the 'JOICO' brand.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_ZuuY0xffLYE.mp4"
] |
neg
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
|
v_ZuuY0xffLYE
| 1,012
| 4
|
In a hair salon, a stylist, with short hair and wearing a black shirt, sprays a hair product on a client's long brown hair, using a large mirror for reference.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a hairstylist and hair products, but it is missing the model with dark hair and the visible 'JOICO' brand on a plain white wall. Query Rewrite: A hairstylist sprays hairspray on a model's dark hair in front of a plain white wall that displays the 'JOICO' brand.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_TT2e7-NbUxo.mp4"
] |
neg
|
1714394113.687865_fig
|
In the background, a hairstylist sprays hairspray on a model's dark hair, with a plain white wall displaying the 'JOICO' brand visible.
|
v_1FMjfLRpXwM
| 3,142
|
v_TT2e7-NbUxo
| 1,016
| 5
|
In a hair salon, a client with short hair sits in a chair while a hairstylist dries and sprays his hair to create a textured, spiky look.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_J4WbF-bJ1T8.mp4"
] |
pos
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of two athletes in a fencing match, but it is missing the animated graphic, grid pattern, interconnected solar panels, and conductive strips that characterize the intended scene. Query Rewrite: An animated graphic features a grid pattern showcasing two fencers alongside interconnected solar panels and conductive strips.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_--mFXNrRZ5E.mp4"
] |
neg
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
|
v_--mFXNrRZ5E
| 873
| 1
|
In this still from a video, two athletes in white uniforms and masks face off in a fencing match, their swords crossing as green lines trace their swift motions against a dark background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of fencers in white uniforms, but it is missing the animated graphic, grid pattern, interconnected solar panels, and conductive strips that characterize the intended scene. Query Rewrite: An animated graphic features a grid pattern showcasing two fencers alongside interconnected solar panels and conductive strips.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_X095EDl0-eU.mp4"
] |
neg
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
|
v_X095EDl0-eU
| 4,838
| 2
|
Two men in white uniforms engage in a fencing match in a dark stadium with a blue floor and spectators in the stands.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of two fencers, but it is missing the animated graphic, grid pattern, interconnected solar panels, and conductive strips that characterize the intended scene. Query Rewrite: An animated graphic features a grid pattern showcasing two fencers alongside interconnected solar panels and conductive strips.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_J5wZTdD4XeU.mp4"
] |
neg
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
|
v_J5wZTdD4XeU
| 4,345
| 3
|
A fencing match takes place between two skilled athletes on a platform in an indoor arena, with one man advancing with a lunge and the other man maintaining a defensive stance, both wearing protective gear and helmets, amidst chairs, a table, and a prominent logo display.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of two adversaries engaged in a combat scenario, but it is missing the animated graphic, the grid pattern, and the elements of solar panels and conductive strips that characterize the intended scene. Query Rewrite: An animated graphic features a grid pattern showcasing two fencers, with interconnected solar panels and conductive strips integrated into the design.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_Vk-aKj0R65o.mp4"
] |
neg
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
|
v_Vk-aKj0R65o
| 9,229
| 4
|
In the confines of a white-walled room, two adversaries clash swords, their focused expressions and determined stances evident as they exchange attacks.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of fencers, but it is missing the animated graphic, grid pattern, interconnected solar panels, and conductive strips that are key elements of the intended scene. Query Rewrite: An animated graphic shows a grid pattern featuring two fencers alongside interconnected solar panels and conductive strips.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_DuLweixeP8I.mp4"
] |
neg
|
1714394113.695243_fig
|
An animated graphic displays a grid pattern of two fencers with interconnected solar panels and conductive strips.
|
v_J4WbF-bJ1T8
| 1,920
|
v_DuLweixeP8I
| 3,493
| 5
|
A guy indicates fencing match outcomes amidst referee and engaged crowd.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_VNMj5YKHEsY.mp4"
] |
pos
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman in both scenes, but it is missing the light-colored hair, the man with a bandage on his head, the red top, the close-up framing, and the blurred indoor background. Query Rewrite: A close-up image of a woman with light-colored hair examining a man wearing a red top and a bandage on his head, with a blurred indoor background.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_yDCZNNI3tDo.mkv"
] |
neg
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
|
v_yDCZNNI3tDo
| 7,937
| 1
|
A woman in a white top smiles and laughs, looking down during a conversation with the camera, while the background shows a beige wall with a light switch.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman and a man, but it is missing the close-up examination of a man with a bandage on his head and a red top, as well as the blurred indoor background. Query Rewrite: A close-up image of a woman with light-colored hair examining a man with a bandage on his head, who is wearing a red top, set against a blurred indoor background.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_tD30qafrkhM.mkv"
] |
neg
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
|
v_tD30qafrkhM
| 5,763
| 2
|
A woman tenderly massages a facial treatment onto a man's closed eyes while he rests comfortably on a bed, adorned with a necklace and sporting a beard.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a person in a close-up image with a blurred background, but it is missing the specific details of a woman with light-colored hair examining a man with a bandage on his head and a red top. Query Rewrite: A close-up image of a woman with light-colored hair examining a man wearing a red top and a bandage on his head, with a blurred indoor background.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_kTStFRAp99E.mp4"
] |
neg
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
|
v_kTStFRAp99E
| 2,559
| 3
|
A girl in a white shirt bends over and rises, her long dark hair concealing her features as the camera captures her from a low angle, with a vague background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman and a man, but it is missing the close-up examination of a man with a bandage on his head and a red top, as well as the blurred indoor background. Query Rewrite: A close-up image of a woman with light-colored hair examining a man with a bandage on his head and wearing a red top, set against a blurred indoor background.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_T8nteSe3U9Q.mp4"
] |
neg
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
|
v_T8nteSe3U9Q
| 451
| 4
|
A man talks to a woman while holding sunblock; she ties her hair.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a close-up image and a woman observing a man, but it is missing the light-colored hair of the woman, the bandage on the man's head, and the blurred indoor background. Query Rewrite: A close-up image of a woman with light-colored hair examining a man with a bandage on his head, who is wearing a red top, set against a blurred indoor background.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_f-r9g_-5huM.mp4"
] |
neg
|
1714394113.714167_fig
|
A woman with light-colored hair examines a man with a bandage on his head and a red top in a close-up image with a blurred indoor background.
|
v_VNMj5YKHEsY
| 77
|
v_f-r9g_-5huM
| 3,394
| 5
|
A man in a black leather jacket with red accents plays a harmonica, with a woman in a white sweater and long dark hair looking on in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_dSHw52PBi5I.mkv"
] |
pos
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring divers performing jumps in an indoor aquatic setting, but it is missing the specific context of the highest diving point marked with the word INDIANA and the cheering spectators present in the intended scene. Query Rewrite: In an indoor swimming pool, divers take turns executing impressive flips from the highest diving point marked with the word INDIANA, landing in the pool while surrounded by cheering spectators.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_vcE8e-fQBhs.mp4"
] |
neg
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
|
v_vcE8e-fQBhs
| 9,653
| 1
|
Divers execute diverse jumps and flips from various platforms at an indoor aquatic center.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring indoor diving activities, but it is missing the specific context of divers taking turns at a high diving point marked with the word INDIANA and the presence of cheering spectators. Query Rewrite: In an indoor swimming pool, divers take turns at a high diving point labeled INDIANA, performing impressive flips before landing in the pool, with spectators cheering around them.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_pzZ4TGcMK1k.mp4"
] |
neg
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
|
v_pzZ4TGcMK1k
| 5,927
| 2
|
Swimmers execute a daring dive from an indoor diving board, spinning three times in mid-air before plunging into a large, well-maintained pool, with a tiled floor and a sign on the wall visible in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both being set in an indoor swimming environment with divers, but it is missing the specific high diving point marked with the word INDIANA and the impressive flips executed by the divers before landing into the pool, as well as the cheering spectators. Query Rewrite: In an indoor swimming pool, divers perform impressive flips from a high diving point labeled INDIANA, landing in the water while surrounded by enthusiastic spectators.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_j_tKuqWYV-A.mp4"
] |
neg
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
|
v_j_tKuqWYV-A
| 207
| 3
|
At an indoor swimming competition, divers take turns diving from a pristine white high dive platform into a clear blue swimming pool, watched by an attentive audience seated on bleachers.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of divers and a cheering crowd, but it is missing the specific context of the highest diving point marked with the word INDIANA and the execution of impressive flips before landing into the pool. Query Rewrite: In an indoor swimming pool, divers take turns at the highest diving point labeled INDIANA, performing impressive flips before landing in the water, while a crowd of spectators cheers them on.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_7EEpIeXhO54.mp4"
] |
neg
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
|
v_7EEpIeXhO54
| 5,042
| 4
|
Indoor diving competition or practice: Several clips show athletes diving into a pool, but some fail mid-air, surrounded by a cheering crowd.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of an indoor swimming pool and divers, but it is missing the specific detail of the highest diving point marked with the word INDIANA and the impressive flips executed by the divers before landing into the pool, surrounded by cheering spectators. Query Rewrite: In an indoor swimming pool, divers take turns executing impressive flips from the highest diving point marked with the word INDIANA, landing into the pool while being cheered on by spectators.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_JA-B3KK9A-I.mp4"
] |
neg
|
1714394113.67749_fig
|
In an indoor swimming pool, divers take turns at the highest diving point, marked with the word INDIANA, executing impressive flips before landing into the pool, surrounded by cheering spectators
|
v_dSHw52PBi5I
| 9,121
|
v_JA-B3KK9A-I
| 3,075
| 5
|
Men in swimsuits perform daring dives from a high yellow diving board into a clear indoor swimming pool, with several other swimmers and divers in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_N3rFdrfE3q8.mp4"
] |
pos
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a young boy outdoors, but it is missing the specific details of the boy's red and black jacket, the action of picking up a rake, and the context of carrying it towards a garden. Query Rewrite: A young boy wearing a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_FhGOGbL-A84.mp4"
] |
neg
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
|
v_FhGOGbL-A84
| 5,335
| 1
|
A young boy is in a yard, wearing a yellow shirt and using a red leaf blower to blow leaves around in front of a house, with some grass and scattered leaves in the yard.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a young boy and the use of red and black colors, but it is missing the action of picking up a rake and carrying it towards a garden, as well as the specific clothing of a red and black jacket. Query Rewrite: A young boy wearing a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_Wr7YbcQ_Q9g.mp4"
] |
neg
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
|
v_Wr7YbcQ_Q9g
| 3,145
| 2
|
A young boy in red shirt and black shorts pushes a red and black gas-powered lawn mower down a suburban sidewalk, mowing the grass near a stop sign and tree, dressed appropriately for the task.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a young child using a rake, but it is missing the specific details of the boy wearing a red and black jacket and carrying the rake towards a garden on a sidewalk. Query Rewrite: A young boy wearing a red and black jacket stands on a sidewalk, carrying a rake towards a garden.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_q8mReXud6fE.mp4"
] |
neg
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
|
v_q8mReXud6fE
| 390
| 3
|
A little kid stands on dry leaves, raking them with a small rake.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a young boy and the action of working outdoors, but it is missing the specific details of the boy wearing a red and black jacket, picking up a rake, and carrying it towards a garden on a sidewalk. Query Rewrite: A young boy wearing a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_-1IlTIWPNs4.mp4"
] |
neg
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
|
v_-1IlTIWPNs4
| 1,004
| 4
|
A young boy in a black jacket and blue pants shovels snow in a snowy residential area, surrounded by houses and vehicles, while speaking into the camera.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of raking leaves and a garden setting, but it is missing the specific details of a young boy in a red and black jacket and the action of picking up a rake to carry it towards the garden. Query Rewrite: A young boy wearing a red and black jacket stands on a sidewalk, picking up a rake and heading towards a garden.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_IcDadC2tw5c.mp4"
] |
neg
|
1714394113.708267_fig
|
A young boy in a red and black jacket stands on a sidewalk, picking up a rake and carrying it towards a garden.
|
v_N3rFdrfE3q8
| 9,145
|
v_IcDadC2tw5c
| 4,979
| 5
|
A person in dark clothing engages in raking leaves on a property with two open garage doors, surrounded by autumn foliage and a blurred residential background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v__NwkwvaC7Bg.mp4"
] |
pos
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a person in a black shirt, but it is missing the calm demeanor of a woman delivering a message in front of a dimly lit hay backdrop with steady composure. Query Rewrite: A woman stands calmly before a dimly lit hay backdrop, delivering a message to the camera while wearing a black shirt.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_Bg_CMSihJl0.mp4"
] |
neg
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
|
v_Bg_CMSihJl0
| 6,089
| 1
|
A girl in a black shirt, holding a microphone and displaying a tattoo on her arm, sits down and talks in a room with a couch and a window view.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman in a dark outfit, but it is missing the calm delivery of a message to the camera and the dimly lit hay backdrop. Query Rewrite: A woman in a black shirt stands calmly before a dimly lit hay backdrop, delivering a message directly to the camera.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_HhbTyPnFVIg.mp4"
] |
neg
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
|
v_HhbTyPnFVIg
| 7,591
| 2
|
The woman, wearing a dark jacket and blonde hair, enters an open workshop area under a wooden structure with a thatched roof, where a pile of wooden logs is located.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman in both scenes, but it is missing the calm delivery of a message to the camera, the black shirt, and the dimly lit hay backdrop. Query Rewrite: A woman in a black shirt stands calmly before a dimly lit hay backdrop, delivering a message directly to the camera.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_iOgmO3MMeH4.mp4"
] |
neg
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
|
v_iOgmO3MMeH4
| 1,755
| 3
|
Katty Perry strolls down the street with a man, both dressed appropriately for the occasion, followed by a scene of her playing the piano in a well-lit room, and finally talking intently with the man.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman and a dark backdrop, but it is missing the calm demeanor, the black shirt, and the specific setting of a dimly lit hay backdrop that characterize the intended scene. Query Rewrite: A woman in a black shirt stands calmly before a dimly lit hay backdrop, delivering a message to the camera with steady composure.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_M1_4oDuh2as.mkv"
] |
neg
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
|
v_M1_4oDuh2as
| 8,119
| 4
|
A middle-aged woman in an apron engages in conversation while holding a white bucket brimming with supplies, set against a dark backdrop.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the dim lighting, but it is missing the calm delivery of a message, the presence of a woman in a black shirt, and the hay backdrop. Query Rewrite: A woman in a black shirt stands calmly before a dimly lit hay backdrop, delivering a message to the camera.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_zuNQFkkyBNo.mp4"
] |
neg
|
1714394113.693596_fig
|
A woman in a black shirt delivers a calm message to the camera, standing before a dimly lit hay backdrop with steady composure.
|
v__NwkwvaC7Bg
| 2,994
|
v_zuNQFkkyBNo
| 244
| 5
|
A woman in a lacy black and white bra sits in a dimly lit room, surrounded by bright spotlights, smoking a cigarette.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_zuNQFkkyBNo.mp4"
] |
pos
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a girl with long blonde hair smoking a cigarette, but it is missing the dimly lit room, the spotlight, the tattoo on her left arm, and the action of pushing her hair back. Query Rewrite: In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm relaxes in a spotlight, pushing her hair back while holding a cigarette.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_bV_X5E1-T50.mp4"
] |
neg
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
|
v_bV_X5E1-T50
| 3,897
| 1
|
A girl with long blonde hair is sitting in front of a colorful wall, smoking a cigarette.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman with blonde hair lighting a cigarette, but it is missing the specific details of the dimly lit room, the young woman's long hair being pushed back, and the tattoo on her left arm. Query Rewrite: In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm relaxes in a spotlight, pushing her hair back while holding a cigarette.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_UIrn2ziRgEM.mp4"
] |
neg
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
|
v_UIrn2ziRgEM
| 1,122
| 2
|
In an indoor environment, a woman with blonde hair lights a cigarette, the background showing a couch and soft lighting.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a blonde woman smoking a cigarette, but it is missing the dimly lit room, the young woman's long blonde hair, the tattoo on her left arm, and the specific action of her relaxing in a spotlight while pushing her hair back. Query Rewrite: In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm relaxes in a spotlight, pushing her hair back while holding a cigarette.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_lwqSz2Q2L-E.mp4"
] |
neg
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
|
v_lwqSz2Q2L-E
| 9,192
| 3
|
A blonde woman in a red dress smokes a cigarette and blows smoke into the air in a red-walled room, with the camera capturing her continuous smoking from various angles.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a young woman with blonde hair smoking a cigarette, but it is missing the dimly lit room, the spotlight, the tattoo on her left arm, and the action of pushing her hair back. Query Rewrite: In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm relaxes in a spotlight, pushing her hair back while holding a cigarette.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_j73Ks4r5tbg.mkv"
] |
neg
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
|
v_j73Ks4r5tbg
| 791
| 4
|
A young woman with blonde hair and red nails sits in a plain bedroom, talking to the camera while smoking a cigarette and displaying a bottle of blue nail polish on a small table.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a woman holding a cigarette, but it is missing the specific details of the dimly lit room, the young woman with long blonde hair, and the tattoo on her left arm. Query Rewrite: In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm relaxes in a spotlight, pushing her hair back while holding a cigarette.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_QCBaT1NJ32E.mp4"
] |
neg
|
1714394113.705878_fig
|
In a dimly lit room, a young woman with long blonde hair and a tattoo on her left arm, relaxes in a spotlight, pushing her hair back and holding a cigarette.
|
v_zuNQFkkyBNo
| 244
|
v_QCBaT1NJ32E
| 5,065
| 5
|
A woman in a room with a couch and blinds on the window, wears a black top and long brown hair, and continues lifting up her cigarette and blowing smoke into the distance.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"Hose washes, squeegee dries: person cleans and finishes Porsche.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_SwQbnQX7LCQ.mp4"
] |
pos
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the act of washing a car, but it is missing the specific details of a person cleaning and finishing a Porsche with a squeegee, as well as the context of the scene being focused on the Porsche rather than a Maserati in a busy parking lot. Query Rewrite: A person uses a hose to wash and a squeegee to dry a Porsche, completing the cleaning process.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_OVf4tUiUqA0.mp4"
] |
neg
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
|
v_OVf4tUiUqA0
| 8,088
| 1
|
A man in a yellow vest washes a black Maserati in a busy parking lot, paying close attention to the car's tires as they are scrubbed with soap.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the overall context of car cleaning, but it is missing the specific actions of washing with a hose and drying with a squeegee, as well as the focus on a person cleaning and finishing a Porsche. Query Rewrite: A person uses a hose to wash and a squeegee to dry a Porsche, completing the cleaning process.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_U20a95sHi8E.mp4"
] |
neg
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
|
v_U20a95sHi8E
| 5,314
| 2
|
Men spray, wipe, and vacuum the car's interiors and exteriors, then roll it out for drying.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the act of cleaning a car, but it is missing the specific details of using a hose and squeegee, the focus on a Porsche, and the completion of the cleaning process by a single person. Query Rewrite: A person uses a hose to wash and a squeegee to dry a Porsche, completing the cleaning process.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_3CJW0qBwwx4.mp4"
] |
neg
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
|
v_3CJW0qBwwx4
| 2,220
| 3
|
A man in a blue shirt cleans a white compact car using a sponge in a garage setting, while others work on the sides.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a person cleaning cars, but it is missing the specific actions of washing with a hose and drying with a squeegee, as well as the focus on finishing a Porsche. Query Rewrite: A person uses a hose to wash and a squeegee to dry while cleaning a Porsche.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_7TOw39_59xo.mp4"
] |
neg
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
|
v_7TOw39_59xo
| 3,997
| 4
|
The person washes and wipes down cars with a pressure washer and yellow rag, focusing on every detail.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Hose washes, squeegee dries: person cleans and finishes Porsche.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the act of cleaning a car, but it is missing the specific actions of washing with a hose and drying with a squeegee, as well as the detail that the car being cleaned is a Porsche. Query Rewrite: A person uses a hose to wash and a squeegee to dry a Porsche, completing the cleaning process.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_srXhWAGzd-s.mp4"
] |
neg
|
1714394113.718649_fig
|
Hose washes, squeegee dries: person cleans and finishes Porsche.
|
v_SwQbnQX7LCQ
| 2,065
|
v_srXhWAGzd-s
| 2,182
| 5
|
A man in black clothes cleans the white car's exterior and interior with cleaner, as evidenced by the close-up of the car's logo, black dashboard, and red wheel interior.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_HCub1SN4X20.mp4"
] |
pos
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the girl's swinging motion, but it is missing the specific details of her black outfit, the yellow handles of the swing, the sandy ground, the grass patches, and the surrounding trees and bushes in the park. Query Rewrite: A girl in a black outfit swings on a swing with yellow handles in a park, jumping off sandy ground and landing on grass patches, surrounded by trees and bushes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_hDV6wQKvKCg.mp4"
] |
neg
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
|
v_hDV6wQKvKCg
| 1,104
| 1
|
The girl's back-and-forth swinging motion is accompanied by her vocal outbursts to the camera.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a swing in a park setting, but it is missing the girl in a black outfit, the yellow handles on the swing, the act of jumping off the sandy ground, and the specific surroundings of bushes and grass patches. Query Rewrite: A girl in a black outfit swings on a swing with yellow handles in a park, jumping off sandy ground and landing on grass patches, surrounded by trees and bushes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_o4uymxrCKeo.mp4"
] |
neg
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
|
v_o4uymxrCKeo
| 9,808
| 2
|
A man in a blue shirt and blue pants swings as high as he can on a swing set with a metal frame, situated on a dirt patch in a park-like setting with grass and trees in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a girl swinging in a park, but it is missing the girl's black outfit, the yellow handles of the swing, the sandy ground, and the grass patches surrounding her, as well as the presence of trees and bushes. Query Rewrite: A girl in a black outfit swings on a swing with yellow handles, jumping off sandy ground and landing on grass patches in a park surrounded by trees and bushes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_W0EN9JeU66A.mp4"
] |
neg
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
|
v_W0EN9JeU66A
| 8,292
| 3
|
A young girl in a pink dress is happily swinging back and forth on a black swing in a park setting, with a blue swing and a bench nearby.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring children swinging in a park, but it is missing the girl in a black outfit, the sandy ground, and the grass patches surrounding the swing. Query Rewrite: A girl in a black outfit swings on a yellow-handled swing in a park, jumping off sandy ground and landing on grass patches, surrounded by trees and bushes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_cKFARm4dsws.mp4"
] |
neg
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
|
v_cKFARm4dsws
| 3,308
| 4
|
A young boy in a black jacket and blue jeans kicks his feet while swinging on a yellow swing seat, soaring high above a swing set with a red bench and green slide, in a park-like setting with a brick building in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a person swinging in a park, but it is missing the specific details of a girl in a black outfit jumping off sandy ground onto grass patches, surrounded by trees and bushes. Query Rewrite: A girl in a black outfit swings on a swing with yellow handles in a park, jumping off sandy ground and landing on grass patches, surrounded by trees and bushes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_YKLZAgdkFrk.mp4"
] |
neg
|
1714394113.675355_fig
|
A girl wearing a black outfit swings on a swing with yellow handles in a park, jumping off the sandy ground and landing on grass patches, surrounded by trees and bushes.
|
v_HCub1SN4X20
| 3,580
|
v_YKLZAgdkFrk
| 4,559
| 5
|
A woman in a white shirt and blue jeans swings on a swing set in a park, holding a banana and looking down at her hand.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_uAKyRSEaY1s.mp4"
] |
pos
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both involving a person solving a Rubik's Cube, but it is missing the specific details of the man finishing the cube at his desk with a computer monitor, keyboard, and mouse, and stopping the timer. Query Rewrite: At 26 seconds, a man at his desk, equipped with a computer monitor, keyboard, and mouse, completes the Rubik's Cube and stops the timer.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_kRMskyrrRcA.mp4"
] |
neg
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
|
v_kRMskyrrRcA
| 2,397
| 1
|
In a dimly lit room, a person wearing a white and gray hoodie solves a Rubik's Cube and clicks a button, placing the red and black cube on the desk.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a person working on a Rubik's Cube at a desk, but it is missing the specific detail of the man stopping the timer after completing the cube and the presence of a computer monitor instead of a laptop. Query Rewrite: At 26 seconds, a man finishes solving a Rubik's Cube at his desk, which has a computer monitor, keyboard, and mouse, and stops the timer.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_jE0XAclET5w.mp4"
] |
neg
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
|
v_jE0XAclET5w
| 3,405
| 2
|
A person works on completing a Rubik's cube with a timer while seated at a table with a laptop, mouse, and cell phone.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a person completing a Rubik's Cube and stopping a timer, but it is missing the specific details of the man at his desk with a computer monitor, keyboard, and mouse, as well as the exact time of 26 seconds. Query Rewrite: At 26 seconds, a man at his desk, equipped with a computer monitor, keyboard, and mouse, finishes solving a Rubik's Cube and stops the timer.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_sYphlW-m1pU.mp4"
] |
neg
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
|
v_sYphlW-m1pU
| 6,578
| 3
|
With a 'REEL' shirt on, a boy completes a Rubik's Cube, places it on the desk, and halts the timer on his computer, displaying '00:00:17'.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man and a Rubik's Cube, but it is missing the completion of the cube, the desk setup with a computer monitor, keyboard, and mouse, and the action of stopping the timer. Query Rewrite: At 26 seconds, a man at his desk, with a computer monitor, keyboard, and mouse, finishes solving a Rubik's Cube and stops the timer.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_5WCgpt2bEJw.mp4"
] |
neg
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
|
v_5WCgpt2bEJw
| 6,518
| 4
|
The man places a timer on the table, presses it, and then reaches for a Rubik's cube.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a man solving a Rubik's Cube at a desk with a computer monitor, but it is missing the specific detail of the man finishing the Rubik's Cube at 26 seconds and stopping the timer. Query Rewrite: At 26 seconds, a man finishes solving a Rubik's Cube at his desk, which has a computer monitor, keyboard, and mouse, and he stops the timer.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_0gvD2pktxxw.mp4"
] |
neg
|
1714394113.735077_fig
|
With a time of 26 seconds, the man finishes the Rubik's Cube at his desk, complete with a computer monitor, keyboard, and mouse, and stops the timer.
|
v_uAKyRSEaY1s
| 5,691
|
v_0gvD2pktxxw
| 3,687
| 5
|
A man, wearing a watch, solves a Rubik's Cube with excitement and clenches his fists, sitting at a desk with a computer monitor showing the time '3.09'.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_LOhacn4jdT4.mp4"
] |
pos
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the context of a weightlifting competition, but it is missing the specific details of the man wearing a blue tank top, black shorts, and red shoes while lifting a red and black weightlifting bar with two weights. Query Rewrite: A man wearing a blue tank top and black shorts, with red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_Kq8g8jjodvc.mkv"
] |
neg
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
|
v_Kq8g8jjodvc
| 8,891
| 1
|
In the midst of a weightlifting competition or training session, a man wearing a sleeveless top and shorts demonstrates strength and control as he lifts a green and red barbell from a squatting position to his chest and then over his head in an indoor setting.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man lifting a barbell in a gym setting, but it is missing the specific details of the man's attire, the color of the shoes, and the context of a weightlifting competition with a red and black weightlifting bar and weights. Query Rewrite: A man wearing a blue tank top and black shorts, with red shoes, is lifting a red and black weightlifting bar with two weights at a weightlifting competition.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_CcMic7jNIuE.mkv"
] |
neg
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
|
v_CcMic7jNIuE
| 6,710
| 2
|
A man in a blue shirt and shorts is lifting a heavy barbell weight in an indoor gym setting, surrounded by colorful weights and a bench.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a man lifting a barbell, but it is missing the specific details of the man's blue tank top, black shorts, red shoes, and the context of a weightlifting competition. Query Rewrite: A man lifts a red and black weightlifting bar with two weights at a weightlifting competition, wearing a blue tank top, black shorts, and red shoes.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_g8Yx4qWzNH0.mp4"
] |
neg
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
|
v_g8Yx4qWzNH0
| 4,059
| 3
|
A man in gym attire, including a sleeveless 'USA' top, shorts, and knee braces, lifts a heavy barbell with weights over his head in a gym setting.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a man lifting weights in a gym setting, but it is missing the specific details of the man wearing a blue tank top and black shorts, lifting a red and black weightlifting bar with two weights at a weightlifting competition. Query Rewrite: A man in a blue tank top and black shorts lifts a red and black weightlifting bar with two weights at a weightlifting competition.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_8TDYCXqSHCw.mp4"
] |
neg
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
|
v_8TDYCXqSHCw
| 7,927
| 4
|
In a gym setting, a man lifts a red dumbbell above his head, showcasing his strength and skill amongst various equipment and gym posters, wearing a blue shirt and dark pants.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both featuring a man lifting a weight during a weightlifting competition, but it is missing the specific details of the man's attire, the type of weightlifting equipment, and the action of lifting without losing balance. Query Rewrite: A man wearing a blue tank top and black shorts, with red shoes, lifts a red and black weightlifting bar with two weights during a weightlifting competition.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_of4bEaqQzOk.mp4"
] |
neg
|
1714394113.732432_fig
|
A man in a blue tank top and black shorts, wearing red shoes, lifts a red and black weightlifting bar with two weights at a weightlifting competition.
|
v_LOhacn4jdT4
| 721
|
v_of4bEaqQzOk
| 3,903
| 5
|
During a weightlifting competition, a man in a blue leotard lifts a red barbell above his head, but loses his balance and falls on his back, causing the barbell to drop.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_avxSMcGBdG8.mp4"
] |
pos
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of players swinging mallets in a grassy area, but it is missing the specific focus on individuals' lower legs, the three black and yellow balls, and the three wooden mallets with black handles. Query Rewrite: Individuals are playing croquet on a grassy area, with a focus on their lower legs, three distinct black and yellow balls, and three wooden mallets featuring black handles.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_TpURw9nc8ks.mp4"
] |
neg
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
|
v_TpURw9nc8ks
| 7,477
| 1
|
Players take turns and swing mallets, hitting colorful balls in a grassy area with wickets.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of players engaging in a game of croquet on a grassy area, but it is missing the specific focus on the lower legs of the individuals, the three black and yellow balls, and the three wooden mallets with black handles. Query Rewrite: Individuals play croquet on a grassy area, with a focus on their lower legs, featuring three black and yellow balls and three wooden mallets with black handles.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_aSFtL7YEbDE.mp4"
] |
neg
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
|
v_aSFtL7YEbDE
| 1,712
| 2
|
Players engage in a friendly game of croquet on a well-manicured grassy field, with three balls, one blue and two orange, positioned near their respective wickets and poles in the background.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both being set on a grassy area with groups of people playing a sport, but it is missing the specific elements of croquet, including the focus on lower legs, three black and yellow balls, and three wooden mallets with black handles. Query Rewrite: Individuals are playing croquet on a grassy area, with a focus on their lower legs, three black and yellow balls, and three wooden mallets with black handles.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_ctFlPn4EfkU.mp4"
] |
neg
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
|
v_ctFlPn4EfkU
| 8,295
| 3
|
A group of people are playing golf on a grassy area with a beautiful backdrop of a building. One person is in the foreground, wearing a black shirt and pants, and is in the process of swinging a golf club at a golf ball. Two golf balls are visible in the image, one near the man and another further away. The grassy area is dotted with people in various stages of their golf game.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a croquet match on a grassy area, but it is missing the focus on individuals' lower legs, the specific colors of the balls (black and yellow), and the wooden mallets with black handles. Query Rewrite: Individuals are playing croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets featuring black handles.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_rgJ00nNS_r0.mp4"
] |
neg
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
|
v_rgJ00nNS_r0
| 2,086
| 4
|
Men engage in a croquet match on a lush grassy field, one player humorously uses his red and white mallet to suggestive effect, surrounded by three croquet balls: one red, one green, and one white.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a croquet game on a grassy area, but it is missing the specific focus on individuals' lower legs, the three black and yellow balls, and the three wooden mallets with black handles. Query Rewrite: Individuals are playing croquet on a grassy area, with a focus on their lower legs, three black and yellow balls, and three wooden mallets featuring black handles.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_eudqfH7Vz_c.mp4"
] |
neg
|
1714394113.730507_fig
|
Individuals play croquet on a grassy area, with the camera focusing on their lower legs, three black and yellow balls, and three wooden mallets with black handles.
|
v_avxSMcGBdG8
| 4,287
|
v_eudqfH7Vz_c
| 5,186
| 5
|
Three boys engage in a lively game of croquet on a sprawling lawn, hitting wickets and maneuvering around each other.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.\""
},
{
"role": "assistant",
"content": "This video contains the moment which describes \"A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.\". The embedding is Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_bTE3HEy_kVk.mp4"
] |
pos
|
1714394113.741532_fig
|
A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.
|
v_bTE3HEy_kVk
| 6,182
| -1
| 0
| null |
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to the presence of a person working on a roof, but it is missing the large pile of pinkish-brown insulation material and the specific action of installation on a metal roofing sheet. Query Rewrite: A person's hand is installing a large pile of pinkish-brown insulation material on a metal roofing sheet.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_2zl0O1VRDC4.mp4"
] |
neg
|
1714394113.741532_fig
|
A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.
|
v_bTE3HEy_kVk
| 6,182
|
v_2zl0O1VRDC4
| 9,679
| 1
|
A person applies sealing material around steel planks and a roof using a white, flexible lid, in a corrugated metal workshop setting.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both involving roofing work, but it is missing the large pile of pinkish-brown insulation material and the visible person's hand involved in the installation process. Query Rewrite: A person's hand is installing a large pile of pinkish-brown insulation material on a metal roofing sheet.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_AJtJcV2_l1Q.mp4"
] |
neg
|
1714394113.741532_fig
|
A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.
|
v_bTE3HEy_kVk
| 6,182
|
v_AJtJcV2_l1Q
| 2,886
| 2
|
A roofer installs shingles, overlapping them and securing with a nail gun.
|
[
{
"role": "system",
"content": "Determine whether the query describes a specific moment that exists in the given video. If the video contains the described moment, represent the query derived from the original query for video retrieval. If it does not, identify which scene or aspect is missing and which misleading cues caused the mismatch. Then rewrite the query by re-weighting the focus: explicitly emphasize the missing or essential elements and de-emphasize the misleading or less relevant ones. Do NOT invent or hallucinate any new details that are not present in the original query. Finally, represent the (original or revised) query for video retrieval."
},
{
"role": "user",
"content": "<video>\nQuery: \"A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.\""
},
{
"role": "assistant",
"content": "This video does not contain the queried moment. The retrieved scene looks similar due to both involving construction activities, but it is missing the specific focus on the installation of pinkish-brown insulation material and the visibility of a person's hand in the process. Query Rewrite: A person's hand is visible as they install a large pile of pinkish-brown insulation material on a metal roofing sheet.. To find the correct video, search for Latent slots: <LAT0> <LAT1> <LAT2> <LAT3> <LAT4> <LAT5> <LAT6> <LAT7> <LAT_EOS>"
}
] |
[
"/hub_data2/dohwan/data/retrieval/activitynet/videos/v_j0FMv4RDpEk.mp4"
] |
neg
|
1714394113.741532_fig
|
A large pile of pinkish-brown insulation material is being installed on a metal roofing sheet, with a person's hand visible in the process.
|
v_bTE3HEy_kVk
| 6,182
|
v_j0FMv4RDpEk
| 6,061
| 3
|
In a construction scene, a man applies roofing material with a spray gun, while his colleague passes him shingles to be attached, ensuring a seamless repair process.
|
End of preview. Expand
in Data Studio
No dataset card yet
- Downloads last month
- 21