The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Error code:   DatasetGenerationError
Exception:    ArrowCapacityError
Message:      array cannot contain more than 2147483646 bytes, have 2523066881
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1995, in _prepare_split_single
                  for _, table in generator:
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 797, in wrapped
                  for item in generator(*args, **kwargs):
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/packaged_modules/json/json.py", line 122, in _generate_tables
                  pa_table = paj.read_json(
                File "pyarrow/_json.pyx", line 308, in pyarrow._json.read_json
                File "pyarrow/error.pxi", line 154, in pyarrow.lib.pyarrow_internal_check_status
                File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
              pyarrow.lib.ArrowCapacityError: array cannot contain more than 2147483646 bytes, have 2523066881
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1524, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1099, in stream_convert_to_parquet
                  builder._prepare_split(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1882, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 2038, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
| image
				 string | bbox
				 sequence | conversations
				 list | 
|---|---|---|
| 
	coco/train2014/COCO_train2014_000000480023.jpg | 
	[
  [
    116,
    305,
    264,
    255
  ],
  [
    75,
    134,
    187,
    207
  ],
  [
    239,
    176,
    101,
    131
  ],
  [
    394,
    222,
    92,
    204
  ],
  [
    0,
    0,
    83,
    161
  ],
  [
    345,
    217,
    56,
    70
  ],
  [
    4,
    128,
    110,
    153
  ],
  [
    381,
    241,
    52,
    58
  ],
  [
    225,
    111,
    68,
    87
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: person\nRegion 3: person\nRegion 4: person\nRegion 5: person\nRegion 6: person\nRegion 7: person\nRegion 8: person\nRegion 9: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000480023.jpg | 
	[
  [
    45,
    402,
    426,
    212
  ],
  [
    0,
    525,
    66,
    126
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000480023.jpg | 
	[
  [
    0,
    236,
    117,
    295
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000050518.jpg | 
	[
  [
    245,
    208,
    40,
    20
  ],
  [
    33,
    223,
    294,
    232
  ],
  [
    214,
    124,
    182,
    335
  ],
  [
    0,
    105,
    56,
    57
  ],
  [
    107,
    0,
    175,
    180
  ],
  [
    315,
    275,
    96,
    201
  ],
  [
    216,
    229,
    30,
    42
  ],
  [
    137,
    228,
    27,
    40
  ],
  [
    0,
    271,
    107,
    156
  ],
  [
    117,
    256,
    44,
    15
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: dining table\nRegion 3: person\nRegion 4: boat\nRegion 5: boat\nRegion 6: bench\nRegion 7: cup\nRegion 8: cup\nRegion 9: bench\nRegion 10: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000142589.jpg | 
	[
  [
    288,
    18,
    206,
    327
  ],
  [
    0,
    29,
    246,
    368
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: bowl"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000209263.jpg | 
	[
  [
    126,
    475,
    74,
    69
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000209263.jpg | 
	[
  [
    58,
    416,
    402,
    208
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000209263.jpg | 
	[
  [
    1,
    30,
    432,
    503
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000015307.jpg | 
	[
  [
    185,
    93,
    231,
    434
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000015307.jpg | 
	[
  [
    191,
    9,
    140,
    76
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000015307.jpg | 
	[
  [
    11,
    16,
    549,
    572
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000328812.jpg | 
	[
  [
    117,
    195,
    136,
    145
  ],
  [
    1,
    1,
    390,
    479
  ],
  [
    0,
    129,
    111,
    243
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: person\nRegion 3: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000328812.jpg | 
	[
  [
    0,
    419,
    80,
    69
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: sandwich"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000246920.jpg | 
	[
  [
    238,
    44,
    272,
    308
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576810.jpg | 
	[
  [
    282,
    213,
    115,
    58
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576810.jpg | 
	[
  [
    0,
    102,
    477,
    315
  ],
  [
    458,
    183,
    165,
    242
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576810.jpg | 
	[
  [
    362,
    171,
    59,
    128
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576810.jpg | 
	[
  [
    504,
    165,
    58,
    46
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576810.jpg | 
	[
  [
    413,
    303,
    109,
    116
  ],
  [
    579,
    170,
    58,
    207
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: handbag\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000046298.jpg | 
	[
  [
    221,
    136,
    121,
    379
  ],
  [
    181,
    150,
    69,
    380
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000046298.jpg | 
	[
  [
    94,
    107,
    108,
    438
  ],
  [
    261,
    82,
    179,
    457
  ],
  [
    80,
    163,
    24,
    207
  ],
  [
    1,
    9,
    484,
    639
  ],
  [
    322,
    159,
    90,
    314
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: bowl\nRegion 5: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    194,
    266,
    251,
    137
  ],
  [
    212,
    249,
    227,
    38
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    256,
    207,
    179,
    51
  ],
  [
    278,
    171,
    135,
    29
  ],
  [
    286,
    183,
    152,
    41
  ],
  [
    55,
    219,
    114,
    167
  ],
  [
    109,
    181,
    87,
    149
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: cup\nRegion 5: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    205,
    138,
    64,
    115
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    295,
    159,
    124,
    11
  ],
  [
    306,
    143,
    106,
    21
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    234,
    101,
    70,
    89
  ],
  [
    113,
    71,
    57,
    49
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: cup\nRegion 2: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000235437.jpg | 
	[
  [
    139,
    157,
    69,
    126
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576993.jpg | 
	[
  [
    57,
    87,
    264,
    197
  ],
  [
    0,
    9,
    457,
    364
  ],
  [
    307,
    143,
    165,
    32
  ],
  [
    437,
    174,
    44,
    40
  ],
  [
    337,
    33,
    21,
    39
  ],
  [
    249,
    0,
    96,
    110
  ],
  [
    151,
    1,
    83,
    99
  ],
  [
    393,
    1,
    36,
    43
  ],
  [
    77,
    0,
    26,
    28
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: dining table\nRegion 3: fork\nRegion 4: knife\nRegion 5: bowl\nRegion 6: cup\nRegion 7: cup\nRegion 8: cup\nRegion 9: knife"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576993.jpg | 
	[
  [
    115,
    11,
    46,
    19
  ],
  [
    1,
    4,
    90,
    39
  ],
  [
    404,
    0,
    82,
    137
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: bowl\nRegion 2: person\nRegion 3: bottle"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576993.jpg | 
	[
  [
    92,
    13,
    168,
    91
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000576993.jpg | 
	[
  [
    0,
    52,
    23,
    29
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: fork"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000329623.jpg | 
	[
  [
    217,
    62,
    45,
    20
  ],
  [
    520,
    357,
    126,
    73
  ],
  [
    43,
    13,
    315,
    276
  ],
  [
    438,
    2,
    197,
    380
  ],
  [
    214,
    0,
    145,
    79
  ],
  [
    428,
    232,
    27,
    52
  ],
  [
    365,
    370,
    82,
    33
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: bottle\nRegion 3: bottle\nRegion 4: person\nRegion 5: person\nRegion 6: knife\nRegion 7: knife"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000329623.jpg | 
	[
  [
    127,
    320,
    154,
    90
  ],
  [
    225,
    144,
    95,
    54
  ],
  [
    146,
    172,
    51,
    49
  ],
  [
    261,
    6,
    116,
    131
  ],
  [
    14,
    128,
    526,
    304
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: apple\nRegion 2: broccoli\nRegion 3: cup\nRegion 4: chair\nRegion 5: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000329623.jpg | 
	[
  [
    18,
    2,
    105,
    55
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000329623.jpg | 
	[
  [
    220,
    178,
    35,
    98
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: bottle"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000257615.jpg | 
	[
  [
    337,
    149,
    273,
    170
  ],
  [
    0,
    80,
    691,
    428
  ],
  [
    172,
    312,
    82,
    85
  ],
  [
    250,
    285,
    70,
    77
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: dining table\nRegion 3: cup\nRegion 4: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000257615.jpg | 
	[
  [
    0,
    53,
    203,
    346
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000124829.jpg | 
	[
  [
    94,
    102,
    587,
    334
  ],
  [
    87,
    109,
    562,
    323
  ],
  [
    88,
    0,
    241,
    152
  ],
  [
    115,
    276,
    416,
    193
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: sandwich\nRegion 3: person\nRegion 4: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568393.jpg | 
	[
  [
    278,
    170,
    89,
    94
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568393.jpg | 
	[
  [
    174,
    93,
    145,
    110
  ],
  [
    3,
    3,
    676,
    512
  ],
  [
    4,
    0,
    80,
    123
  ],
  [
    511,
    0,
    39,
    52
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: sandwich\nRegion 2: dining table\nRegion 3: cup\nRegion 4: spoon"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568393.jpg | 
	[
  [
    69,
    42,
    30,
    67
  ],
  [
    435,
    0,
    84,
    34
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: spoon\nRegion 2: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    183,
    372,
    47,
    36
  ],
  [
    258,
    272,
    19,
    27
  ],
  [
    272,
    276,
    18,
    27
  ],
  [
    474,
    435,
    28,
    46
  ],
  [
    157,
    239,
    412,
    233
  ],
  [
    389,
    8,
    154,
    374
  ],
  [
    385,
    67,
    260,
    432
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: bottle\nRegion 5: dining table\nRegion 6: person\nRegion 7: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    363,
    87,
    95,
    223
  ],
  [
    3,
    79,
    221,
    386
  ],
  [
    10,
    38,
    125,
    172
  ],
  [
    494,
    409,
    37,
    58
  ],
  [
    387,
    340,
    9,
    34
  ],
  [
    444,
    384,
    43,
    72
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person\nRegion 3: person\nRegion 4: cup\nRegion 5: fork\nRegion 6: spoon"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    364,
    401,
    27,
    47
  ],
  [
    365,
    398,
    113,
    85
  ],
  [
    314,
    311,
    78,
    49
  ],
  [
    326,
    347,
    103,
    74
  ],
  [
    270,
    309,
    60,
    35
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: spoon\nRegion 2: bowl\nRegion 3: bowl\nRegion 4: bowl\nRegion 5: bowl"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    261,
    431,
    92,
    52
  ],
  [
    336,
    202,
    19,
    32
  ],
  [
    351,
    198,
    15,
    41
  ],
  [
    359,
    201,
    17,
    36
  ],
  [
    204,
    211,
    12,
    15
  ],
  [
    385,
    338,
    14,
    35
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: bowl\nRegion 2: bottle\nRegion 3: bottle\nRegion 4: bottle\nRegion 5: cup\nRegion 6: spoon"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    287,
    303,
    45,
    36
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: spoon"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    272,
    395,
    53,
    20
  ],
  [
    190,
    363,
    17,
    22
  ],
  [
    226,
    390,
    70,
    48
  ],
  [
    266,
    300,
    17,
    12
  ],
  [
    225,
    271,
    30,
    20
  ],
  [
    241,
    299,
    14,
    13
  ],
  [
    321,
    158,
    54,
    8
  ],
  [
    269,
    68,
    56,
    137
  ],
  [
    249,
    126,
    30,
    44
  ],
  [
    209,
    133,
    44,
    40
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: spoon\nRegion 2: spoon\nRegion 3: bowl\nRegion 4: hot dog\nRegion 5: hot dog\nRegion 6: hot dog\nRegion 7: dining table\nRegion 8: person\nRegion 9: person\nRegion 10: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    0,
    104,
    18,
    102
  ],
  [
    116,
    66,
    25,
    69
  ],
  [
    391,
    413,
    60,
    47
  ],
  [
    277,
    82,
    16,
    19
  ],
  [
    0,
    207,
    62,
    89
  ],
  [
    227,
    284,
    20,
    21
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person\nRegion 3: carrot\nRegion 4: person\nRegion 5: person\nRegion 6: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    394,
    219,
    44,
    10
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495875.jpg | 
	[
  [
    343,
    271,
    33,
    16
  ],
  [
    259,
    229,
    12,
    16
  ],
  [
    268,
    227,
    11,
    20
  ],
  [
    276,
    227,
    21,
    18
  ],
  [
    184,
    178,
    85,
    63
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog\nRegion 5: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000117601.jpg | 
	[
  [
    243,
    210,
    293,
    201
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000117601.jpg | 
	[
  [
    143,
    43,
    143,
    126
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000117601.jpg | 
	[
  [
    0,
    89,
    209,
    326
  ],
  [
    142,
    268,
    279,
    165
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000117601.jpg | 
	[
  [
    144,
    43,
    151,
    111
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: sandwich"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000316170.jpg | 
	[
  [
    314,
    248,
    122,
    36
  ],
  [
    331,
    118,
    108,
    99
  ],
  [
    440,
    62,
    82,
    126
  ],
  [
    118,
    120,
    170,
    132
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: cup\nRegion 3: cup\nRegion 4: bowl"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000316170.jpg | 
	[
  [
    189,
    226,
    260,
    143
  ],
  [
    466,
    199,
    118,
    159
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: bowl\nRegion 2: cup"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000439602.jpg | 
	[
  [
    0,
    3,
    571,
    308
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000354530.jpg | 
	[
  [
    17,
    1,
    506,
    296
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000300070.jpg | 
	[
  [
    156,
    239,
    249,
    72
  ],
  [
    495,
    51,
    59,
    169
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: bottle"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000300070.jpg | 
	[
  [
    1,
    1,
    327,
    307
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000300070.jpg | 
	[
  [
    114,
    338,
    516,
    123
  ],
  [
    431,
    270,
    60,
    34
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dining table\nRegion 2: fork"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000197739.jpg | 
	[
  [
    189,
    401,
    103,
    54
  ],
  [
    246,
    0,
    177,
    282
  ],
  [
    2,
    175,
    329,
    409
  ],
  [
    256,
    480,
    73,
    64
  ],
  [
    282,
    241,
    52,
    79
  ],
  [
    262,
    329,
    37,
    96
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: chair\nRegion 3: person\nRegion 4: sandwich\nRegion 5: potted plant\nRegion 6: fork"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000197739.jpg | 
	[
  [
    144,
    99,
    252,
    470
  ],
  [
    289,
    545,
    62,
    38
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000167683.jpg | 
	[
  [
    380,
    249,
    50,
    47
  ],
  [
    467,
    267,
    81,
    29
  ],
  [
    457,
    226,
    71,
    62
  ],
  [
    421,
    245,
    39,
    45
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000167683.jpg | 
	[
  [
    163,
    269,
    83,
    41
  ],
  [
    280,
    40,
    211,
    234
  ],
  [
    467,
    225,
    32,
    48
  ],
  [
    382,
    251,
    48,
    42
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: person\nRegion 3: sandwich\nRegion 4: sandwich"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000250922.jpg | 
	[
  [
    119,
    247,
    164,
    120
  ],
  [
    520,
    98,
    74,
    34
  ],
  [
    471,
    1,
    154,
    485
  ],
  [
    37,
    0,
    154,
    87
  ],
  [
    2,
    67,
    332,
    349
  ],
  [
    291,
    7,
    209,
    449
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: bottle\nRegion 3: chair\nRegion 4: chair\nRegion 5: dining table\nRegion 6: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000528892.jpg | 
	[
  [
    120,
    332,
    81,
    80
  ],
  [
    22,
    306,
    95,
    65
  ],
  [
    108,
    335,
    63,
    75
  ],
  [
    87,
    334,
    48,
    56
  ],
  [
    335,
    77,
    52,
    137
  ],
  [
    277,
    129,
    55,
    101
  ],
  [
    212,
    33,
    104,
    84
  ],
  [
    486,
    69,
    162,
    210
  ],
  [
    5,
    103,
    583,
    385
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog\nRegion 5: bottle\nRegion 6: bottle\nRegion 7: chair\nRegion 8: chair\nRegion 9: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000528892.jpg | 
	[
  [
    215,
    160,
    7,
    20
  ],
  [
    395,
    190,
    91,
    75
  ],
  [
    87,
    110,
    119,
    72
  ],
  [
    484,
    232,
    98,
    81
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: fork\nRegion 2: bowl\nRegion 3: bowl\nRegion 4: bowl"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000528892.jpg | 
	[
  [
    505,
    265,
    46,
    19
  ],
  [
    131,
    231,
    65,
    34
  ],
  [
    196,
    212,
    31,
    28
  ],
  [
    194,
    195,
    40,
    41
  ],
  [
    154,
    220,
    15,
    9
  ],
  [
    29,
    109,
    55,
    17
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: broccoli\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog\nRegion 5: hot dog\nRegion 6: book"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000528892.jpg | 
	[
  [
    33,
    121,
    53,
    40
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: book"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000166141.jpg | 
	[
  [
    199,
    233,
    86,
    43
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000166141.jpg | 
	[
  [
    205,
    60,
    310,
    396
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000166141.jpg | 
	[
  [
    1,
    1,
    233,
    431
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000520155.jpg | 
	[
  [
    260,
    340,
    309,
    124
  ],
  [
    256,
    340,
    277,
    127
  ],
  [
    43,
    128,
    468,
    441
  ],
  [
    454,
    189,
    129,
    433
  ],
  [
    50,
    47,
    107,
    92
  ],
  [
    310,
    264,
    5,
    12
  ],
  [
    350,
    252,
    5,
    9
  ],
  [
    412,
    341,
    9,
    17
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: sandwich\nRegion 3: person\nRegion 4: person\nRegion 5: person\nRegion 6: person\nRegion 7: person\nRegion 8: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000520155.jpg | 
	[
  [
    344,
    271,
    11,
    14
  ],
  [
    326,
    285,
    8,
    8
  ],
  [
    376,
    302,
    5,
    13
  ],
  [
    421,
    323,
    6,
    8
  ],
  [
    441,
    320,
    6,
    11
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person\nRegion 3: person\nRegion 4: person\nRegion 5: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000520155.jpg | 
	[
  [
    406,
    326,
    7,
    9
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000399408.jpg | 
	[
  [
    83,
    126,
    266,
    106
  ],
  [
    64,
    191,
    326,
    69
  ],
  [
    352,
    0,
    115,
    98
  ],
  [
    0,
    0,
    687,
    346
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: cup\nRegion 4: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000238589.jpg | 
	[
  [
    188,
    396,
    206,
    61
  ],
  [
    613,
    132,
    28,
    23
  ],
  [
    240,
    291,
    36,
    52
  ],
  [
    154,
    374,
    33,
    68
  ],
  [
    5,
    280,
    190,
    199
  ],
  [
    108,
    238,
    120,
    172
  ],
  [
    162,
    220,
    88,
    133
  ],
  [
    213,
    192,
    69,
    100
  ],
  [
    261,
    220,
    84,
    116
  ],
  [
    177,
    32,
    413,
    440
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: chair\nRegion 3: chair\nRegion 4: chair\nRegion 5: person\nRegion 6: person\nRegion 7: person\nRegion 8: person\nRegion 9: person\nRegion 10: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000238589.jpg | 
	[
  [
    474,
    110,
    100,
    138
  ],
  [
    462,
    89,
    27,
    29
  ],
  [
    90,
    192,
    4,
    7
  ],
  [
    457,
    113,
    41,
    60
  ],
  [
    542,
    0,
    106,
    149
  ],
  [
    0,
    406,
    32,
    54
  ],
  [
    599,
    328,
    39,
    159
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person\nRegion 3: person\nRegion 4: person\nRegion 5: person\nRegion 6: chair\nRegion 7: chair"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000238589.jpg | 
	[
  [
    598,
    309,
    29,
    21
  ],
  [
    260,
    198,
    16,
    33
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: bottle\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000238589.jpg | 
	[
  [
    568,
    155,
    36,
    107
  ],
  [
    608,
    174,
    32,
    80
  ],
  [
    499,
    85,
    35,
    35
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: chair\nRegion 2: chair\nRegion 3: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000238589.jpg | 
	[
  [
    244,
    166,
    82,
    51
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000185623.jpg | 
	[
  [
    158,
    60,
    180,
    345
  ],
  [
    357,
    0,
    153,
    352
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: bottle"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000303586.jpg | 
	[
  [
    2,
    251,
    444,
    348
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000303586.jpg | 
	[
  [
    27,
    1,
    160,
    147
  ],
  [
    0,
    48,
    642,
    139
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: wine glass\nRegion 2: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000099077.jpg | 
	[
  [
    112,
    353,
    376,
    89
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000099077.jpg | 
	[
  [
    19,
    1,
    455,
    368
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000338077.jpg | 
	[
  [
    106,
    310,
    197,
    268
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000338077.jpg | 
	[
  [
    0,
    2,
    430,
    655
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000280721.jpg | 
	[
  [
    56,
    127,
    470,
    252
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568098.jpg | 
	[
  [
    365,
    340,
    145,
    53
  ],
  [
    147,
    344,
    84,
    36
  ],
  [
    254,
    366,
    106,
    21
  ],
  [
    541,
    323,
    53,
    26
  ],
  [
    194,
    176,
    62,
    129
  ],
  [
    20,
    276,
    559,
    105
  ],
  [
    91,
    114,
    105,
    190
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog\nRegion 5: person\nRegion 6: hot dog\nRegion 7: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568098.jpg | 
	[
  [
    386,
    173,
    63,
    143
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568098.jpg | 
	[
  [
    591,
    246,
    34,
    70
  ],
  [
    616,
    244,
    26,
    58
  ],
  [
    628,
    242,
    12,
    42
  ],
  [
    0,
    135,
    9,
    76
  ],
  [
    438,
    37,
    146,
    252
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: person\nRegion 3: person\nRegion 4: person\nRegion 5: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568098.jpg | 
	[
  [
    95,
    318,
    67,
    27
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000568098.jpg | 
	[
  [
    33,
    249,
    122,
    23
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: dining table"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000009698.jpg | 
	[
  [
    12,
    48,
    159,
    120
  ],
  [
    338,
    36,
    198,
    182
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000009698.jpg | 
	[
  [
    16,
    45,
    155,
    115
  ],
  [
    0,
    0,
    596,
    371
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: sandwich\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495077.jpg | 
	[
  [
    499,
    256,
    66,
    143
  ],
  [
    183,
    268,
    25,
    122
  ],
  [
    23,
    236,
    124,
    140
  ],
  [
    351,
    235,
    130,
    143
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: hot dog\nRegion 3: hot dog\nRegion 4: hot dog"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495077.jpg | 
	[
  [
    147,
    237,
    109,
    159
  ],
  [
    351,
    2,
    316,
    247
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: hot dog\nRegion 2: person"
  }
] | 
| 
	coco/train2014/COCO_train2014_000000495077.jpg | 
	[
  [
    35,
    2,
    267,
    251
  ],
  [
    87,
    116,
    112,
    66
  ]
] | 
		
	[
  {
    "from": "human",
    "value": "Please identify the labels of each marked region in the image. "
  },
  {
    "from": "gpt",
    "value": "Region 1: person\nRegion 2: knife"
  }
] | 
🎨 Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
The interaction between humans and artificial intelligence (AI) is a crucial factor that reflects the effectiveness of multimodal large language models (MLLMs). However, current MLLMs primarily focus on image-level comprehension and limit interaction to textual instructions, thereby constraining their flexibility in usage and depth of response. Therefore, we introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting.
Training and Evaluation Dataset Card
- MDVP-Data is a comprehensive dataset for multi-domain visual-prompt instruction tuning. This dataset encompasses data for both point-level and region-level understanding, designed to enhance a model’s comprehension ability and robustness. 
- We also introduce MDVP-Bench, a challenging benchmark designed to evaluate tasks that require a combination of detailed description referrals, inter-relationship analysis, and complex reasoning. 
Paper and Code
Project Page: Draw-and-Understand 
Paper: https://arxiv.org/abs/2403.20271 
Code: https://github.com/AFeng-x/Draw-and-Understand
License
Attribution-NonCommercial 4.0 International 
It should abide by the policy of OpenAI: https://openai.com/policies/terms-of-use.
Citations
@misc{lin2024drawandunderstand,
      title={Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want}, 
      author={Weifeng Lin and Xinyu Wei and Ruichuan An and Peng Gao and Bocheng Zou and Yulin Luo and Siyuan Huang and Shanghang Zhang and Hongsheng Li},
      year={2024},
      eprint={2403.20271},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
- Downloads last month
- 426