Dataset Viewer
Auto-converted to Parquet Duplicate
id
stringlengths
22
36
image
imagewidth (px)
384
752
category
stringclasses
1 value
conversations
listlengths
2
2
fadbdcdc-16f8-4f76-b764-75f892a1da45
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the dresser (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "valu...
f4717e50-be28-46ca-b240-13da8bf97f19
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the television (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt"...
Rb2JGSSUTnNwJ26Q8jBs4e
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
aqCT773gJrE8QgQYj8uJs6
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
c1251b7f-d776-4c39-b093-1e61899f2356
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the chair (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "g...
5a3052f3-f21c-4bd9-977f-336da36ae6f2
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the curtain (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": ...
1ae8598d-22ee-47bd-880f-fa490efc1e48
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the bin (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value": ...
Dz6AeZVAyhKGHLZAnRxgGW
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
35ef7f9d-319a-4c42-8d0b-4322d1b1c998
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the counter (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "valu...
R8Hm9jsQ5Tew3aJqjmpXmR
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
mxpZKbnn3ZCJJsGTqDw2iw
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
9gXenwKHj3WdjxhqXMps6U
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
MmUjvBg8xRBDc5T5uQuQJp
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
ec7d0a60-1e23-4eda-9710-fabffd26b906
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the book (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value":...
f5goN6xJt5iHPvSgekJFZZ
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
3Msm9biBq7mqv8nPSh3e74
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
Wtb3V6dED5VhUgCgC4DqVb
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
KmTVweJr23eXwqBWRXXAyF
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
Wi4NVFMBB5dZFKUmTkqqdD
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
f9a82bfd-2c93-47ab-8328-cea26fdabf16
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the microwave (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "va...
dd7a996c-7747-4efd-9e48-5cf087908cb4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the door (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6, F. 6-7, G. 7-8" }, {...
Qyg2XgYfPw8PS6a5ApM8js
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
WzetUYX3dQjXcLJbrVemrB
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
fE4WpVguDbSTLVHFe4FsTg
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
9587b071-ca68-4d6d-a302-9f2a280ae83a
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the plant (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value"...
Vofnbj4DCtafsbGxnaSE3Y
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
2LX3wboHMXWJ3uzs76RCJn
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
b5134f82-c32f-4151-bfcb-50c95692b262
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the lamp (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "gp...
728b4e3b-504a-4e1d-aa09-95bdc7374af5
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the blanket (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "valu...
VisHUNYGNqwmTuqXN8AvK4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
dda6e4d3-f256-4a7e-825b-63988cad951f
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the sofa (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt", ...
cUPnwzzZmXw63MSqPrggCJ
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
3XVKdNwcUAuVo65yKmBZZp
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
LACkZiYXeoFA9qjabXiCS8
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
UkV4d5P9VztGqjYibfXkVC
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
a1d671dc-8177-489c-a313-cf5ed4c2d1df
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the drawer (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value...
haDyRZTXbozYdBJXovBvir
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
X6HNNgqcT3Hk88CkNJ3Z7v
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
702eb5da-4566-4f7b-b40c-86071bae6df4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the picture (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6, F. 6-7" }, { ...
ZW3UqpR2kF6e7crKV7esbG
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
o882mhqpfDJKFZAypBR3kd
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
493d09af-df40-4bf0-94d9-8125d1f17c21
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the chair (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "g...
8HTvDBPAbKN34ozW7tQs87
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
6jqL5FSdu7ewhCqs53wnan
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
hwiTiSeqGQs5F5KtxfEgtM
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
7477eb10-439d-435c-ab20-cc13ad46ce2b
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the chair (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "g...
U9EPCcz7ALEGsYPK5EJNPY
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
a4eFyJBrNNGmgap8sQNeyh
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
a4534790-9b3b-4caa-bdb0-ac78d767f0fe
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the door (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6, F. 6-7, G. 7-8" }, {...
CBHwRPHevyXB93yGYcCDA3
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
NkVKpbVkeZJU6ZUKBoFcWx
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
0394055f-116f-4c8f-ade1-10a7f6b174a8
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the monitor (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": ...
3gpmPdoXSHpxjqAAJzP5kC
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
b34f52f9-02b8-43be-8288-c12574a2b55b
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the curtain (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": ...
5075cf67-0b0d-4afd-b0c8-5cf975d3481c
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the clothes (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt", ...
a8f1b787-2e23-426c-89b1-e425f555c344
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the door (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6, F. 6-7, G. 7-8" }, {...
XTncVz2SyGTYH3r2M6eX2s
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
616f06ea-e7dc-4995-872c-3dbd3e2a1f8b
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the bookshelf (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from"...
m2BTjUXfrq8Py4eEy7t86b
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
e434965b-8f75-4868-b917-662e874aa643
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cabinet (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6, F. 6-7" }, { ...
bc1027c3-3212-4b8a-859e-d5b89f6cf7b7
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the paper (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value"...
42284357-5ed9-4b5c-9d59-5d1981bec41e
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the microwave (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "va...
a944d317-6fe7-430f-a05e-f3976ce84258
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the bookshelf (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from"...
dd6b76c5-f95c-48ad-b727-0e3cfb2c5d6d
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the monitor (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": ...
b123efad-537c-4661-b61c-8ec2cdb84e28
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the chair (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "g...
U7DNeTMALnxQYzEDHpeXLJ
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
iUwTfQuw7uP5u9VWHYmNF4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
6839a9c8-ac57-4d9e-86ec-6a995f1e0d3e
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pillow (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt", ...
dbf6c514-1f1c-4cb0-8003-feddd6e1e7c4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the television (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt"...
WohUChV4kZGKjQo9vkt267
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
UsrQBPMnrGxxnknzJQH95h
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
i2ULhD8fcLnvPArRws5P7k
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
JZGz7YizDcKmDiANhM5Zpb
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
8214c4fa-c242-4549-b1d9-1019eeac41ad
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the night stand (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "...
7a495757-f098-4a35-92be-d88e626aaddf
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the stool (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value"...
5tGzVSW5LRohLUUL5ibZSN
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
S9pEE5CoTi3XQtFroeLChw
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
EB9N6k7AVCagbnnn2STVr5
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
dH8mKjfucnmYgbBJwcWUPt
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
QSzmcCz4VtXmrvcMBdJCa3
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
Kc8LZtTf5zBQpzpLUYi7CK
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
Pz67J7jhwVvfQdYzuxQ8NN
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
WdAkJye7RcVHai8KXf7XoZ
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
azfDMZwVrpieqTR9PEwgnd
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
768fd7a9-3211-4094-a693-1f5939224ad4
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the paper (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value"...
dTGzxYfrccboyZYYkWYCY6
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
04ba7a64-5881-457a-bf41-263d53b0b949
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the bag (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value": ...
H639Rj4N8bX9MYHAqBJB8r
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the cyclist (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 1...
aNkpaXtLDjUhGwxL8qXFEK
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
9dc684e6-aad6-428d-8b51-f9ad9d6f33aa
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the monitor (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": ...
JiJxMtzgPnMzXk4K22FjcT
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
36wGfrsc34rcBXXeSK7oPP
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
hvoNpwfzS3cckZXVjeKwdo
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the car (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
17e09461-d050-4f24-aece-4cf266a3659f
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the paper (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "value"...
bviM9CNinnoQaoYJpGRHjT
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
53a4dfc4-db68-4f60-8518-8889b57ae498
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the blinds (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5, E. 5-6" }, { "from": "...
U3ZWoD5b9nWWmbCSVNR3cD
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the van (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G. 14-15...
b0f47469-981c-4cd5-abed-8c664cedd8e9
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the sofa (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4, D. 4-5" }, { "from": "gpt", ...
h5JUAdFUDiyzshBxgUDphr
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the pedestrian (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 8-9, B. 9-10, C. 10-11, D. 11-12, E. 12-13, F. 13-14, G...
bac22c93-79d7-4680-93fb-8a929d7f7b1a
internal
[ { "from": "human", "value": "<image>\nFrom the camera's perspective, estimate how far the closest point of the night stand (highlighted by a red box) is from the camera in real-world distance, in meters. Select the best answer from the options below: A. 1-2, B. 2-3, C. 3-4" }, { "from": "gpt", "...
End of preview. Expand in Data Studio

AVA-Bench

Training dataset for the paper AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models (arXiv:2506.09082) accepted in CVPR 2026.

AVA-Bench is a diagnostic benchmark for evaluating Vision Foundation Models (VFMs) through Atomic Visual Abilities (AVAs): fundamental perceptual skills such as localization, counting, OCR, spatial understanding, depth estimation, color recognition, texture recognition, and fine-grained recognition.

AVA-Bench disentangls visual perception into 14 atomic visual capabilities, each with distribution-matched training and evaluation splits. This allows researchers to measure where a VFM excels or fails and to construct capability-level “ability fingerprints” for model comparison and selection.

This Hub release contains the training split of AVA-Bench. The evaluation split is released separately; see the project page and paper for details.

Capabilities

AVA-Bench covers 14 atomic visual capabilities, each released as its own subset/config:

Capability Tests
Action Recognizing human/animal actions in images
Color Identifying object colors
Counting Counting instances of an object
Emotion Recognizing emotion from facial expressions/scenes
Fine-grained Fine-grained category discrimination, such as bird, plant, animal, fungi, or aircraft categories
Localization Locating objects via bounding-box queries
OCR Reading text rendered in images
Orientation Determining the orientation or pose of objects
Recognition Object/entity recognition
Scene_Classification Classifying the overall scene/place
Spatial Reasoning about spatial relationships between objects
Texture Identifying surface textures
Absolute_depth Estimating absolute depth from a single image
Relative_depth Comparing depth between two regions

Dataset structure

Each subset has a single train split, stored as Parquet shards with image bytes embedded in the file.

Data fields

Every example contains:

  • image (datasets.Image) — the input image, decoded as a PIL image on access.
  • id (string) — unique example identifier.
  • conversations (list of {from, value}) — instruction-tuning style turns. The human turn includes the question, usually with an <image> placeholder, and the gpt turn includes the ground-truth answer.

Some capabilities may additionally include fields such as:

  • height
  • width
  • category
  • area
  • bounding-box or region metadata, depending on the capability Per-subset row counts are visible in the dataset viewer's config dropdown.

Usage

Please go to github to use the dataset to evaluate Vision Foundation Models. If you want to check the dataset:

from datasets import load_dataset

# Load one capability
ds = load_dataset("act13/AVA-Bench", name="Counting", split="train")

print(ds[0])
# {
#   'id': '...',
#   'image': <PIL.Image.Image image mode=RGB ...>,
#   'conversations': [
#       {'from': 'human', 'value': '<image>\n...'},
#       {'from': 'gpt', 'value': '...'}
#   ],
#   ...
# }

To stream without downloading the full subset:

from datasets import load_dataset

ds = load_dataset(
    "act13/AVA-Bench",
    name="Counting",
    split="train",
    streaming=True,
)

for ex in ds.take(5):
    print(ex["conversations"][0]["value"])
    print(ex["conversations"][1]["value"])

Intended uses

AVA-Bench is intended for research on vision foundation models and vision-language systems. Suitable uses include:

  • Training or instruction-tuning vision-language models on atomic visual abilities.
  • Diagnosing which visual capabilities a VFM lacks.
  • Comparing VFMs through capability-level performance rather than only aggregate VQA accuracy.
  • Constructing balanced training mixtures across visual abilities.
  • Studying how different VFM pretraining objectives affect downstream perceptual capabilities.

Source datasets

AVA-Bench is curated from multiple existing datasets, depending on the atomic visual ability. Source datasets include, but are not necessarily limited to:

  • Objects365
  • LVIS
  • iNaturalist-2021
  • DIOR
  • NYU-Depth V2
  • KITTI
  • COCO-Text
  • IIIT5K
  • TextVQA
  • EgoOrientBench
  • CURE-OR
  • Places434
  • AID
  • CUB-200-2011
  • FGVC-Aircraft
  • MiT
  • DTD
  • Kylberg
  • KTH-TIPS
  • KTH-TIPS2

Please see the paper for the full per-capability dataset construction details and source-license breakdown.

License

This dataset card and the AVA-Bench organization/annotations are released under CC-BY-4.0.

Underlying images retain the licenses of their original source datasets. Users are responsible for respecting the license terms and usage restrictions of each source dataset.

Citation

If you use AVA-Bench, please cite:

@article{mai2025ava,
  title={Ava-bench: Atomic visual ability benchmark for vision foundation models},
  author={Mai, Zheda and Chowdhury, Arpita and Wang, Zihe and Jeon, Sooyoung and Wang, Lemeng and Hou, Jiacheng and Chao, Wei-Lun},
  journal={arXiv preprint arXiv:2506.09082},
  year={2025}
}

Contact

Open a discussion on this dataset's Community tab, or reach the authors via the contact information provided in the paper.

Downloads last month
-

Paper for act13/AVA-Bench