Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code:   DatasetGenerationCastError
Exception:    DatasetGenerationCastError
Message:      An error occurred while generating the dataset

All the data files must have the same columns, but at some point there are 1 new columns ({'score'}) and 3 missing columns ({'width', 'image', 'height'}).

This happened while the json dataset builder was generating data using

hf://datasets/tyfeld/underwood/text_data/gsm8k_train_socratic_en.jsonl (at revision 0fa1efb609a5bd3b060f3a178c5f3890f0d13230)

Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1831, in _prepare_split_single
                  writer.write_table(table)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 644, in write_table
                  pa_table = table_cast(pa_table, self._schema)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2272, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2218, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              id: int64
              conversations: list<item: struct<from: string, value: string>>
                child 0, item: struct<from: string, value: string>
                    child 0, from: string
                    child 1, value: string
              score: double
              to
              {'id': Value('int64'), 'image': Value('string'), 'width': Value('int64'), 'height': Value('int64'), 'conversations': List({'from': Value('string'), 'value': Value('string')})}
              because column names don't match
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1451, 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 994, in stream_convert_to_parquet
                  builder._prepare_split(
                File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1702, 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 1833, in _prepare_split_single
                  raise DatasetGenerationCastError.from_cast_error(
              datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
              
              All the data files must have the same columns, but at some point there are 1 new columns ({'score'}) and 3 missing columns ({'width', 'image', 'height'}).
              
              This happened while the json dataset builder was generating data using
              
              hf://datasets/tyfeld/underwood/text_data/gsm8k_train_socratic_en.jsonl (at revision 0fa1efb609a5bd3b060f3a178c5f3890f0d13230)
              
              Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

id
int64
image
string
width
int64
height
int64
conversations
list
0
images/53951.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor question: <ref>select the favourite icon which is on the left side of the page</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>select the favourite icon which is on the left side of the page</ref><box>[[10, 743, 82, 783]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box that can finalize the instruction: <ref>select the edit icon which is at the bottom right corner of the page</ref>." }, { "from": "gpt", "value": "<ref>select the edit icon which is at the bottom right corner of the page</ref><box>[[863, 827, 971, 888]]</box>" } ]
1
images/39509.jpg
540
960
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for solving the task: <ref>select the button got it dismiss this</ref>." }, { "from": "gpt", "value": "<ref>select the button got it dismiss this</ref><box>[[237, 627, 761, 684]]</box>" } ]
2
images/29984.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the instruction: <ref>click the third image</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click the third image</ref><box>[[38, 310, 155, 376]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>click on podcasts option</ref>." }, { "from": "gpt", "value": "<ref>click on podcasts option</ref><box>[[871, 790, 1000, 852]]</box>" }, { "from": "human", "value": "What is the bounding box coordinates that is most relevant to this task: <ref>select the 6th share icon</ref>." }, { "from": "gpt", "value": "<ref>select the 6th share icon</ref><box>[[883, 547, 961, 613]]</box>" }, { "from": "human", "value": "What are the precise coordinates of the bounding box where I can click to finalize the instruction: <ref>click on the second option</ref>." }, { "from": "gpt", "value": "<ref>click on the second option</ref><box>[[38, 231, 155, 297]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box that can finalize the instruction: <ref>select the fifth share icon</ref>." }, { "from": "gpt", "value": "<ref>select the fifth share icon</ref><box>[[883, 468, 961, 534]]</box>" }, { "from": "human", "value": "Show the bounding box coordinates to click for completing the objective: <ref>select the second picture from the bottom</ref>." }, { "from": "gpt", "value": "<ref>select the second picture from the bottom</ref><box>[[38, 626, 155, 691]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for completing the objective: <ref>click on the image which is just above the play icon</ref>." }, { "from": "gpt", "value": "<ref>click on the image which is just above the play icon</ref><box>[[38, 705, 155, 770]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>click on the top right corner option</ref>." }, { "from": "gpt", "value": "<ref>click on the top right corner option</ref><box>[[902, 38, 1000, 104]]</box>" } ]
3
images/52042.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nShow the bounding box coordinates to click for completing the objective: <ref>click on icon left to bookmarks</ref>." }, { "from": "gpt", "value": "<ref>click on icon left to bookmarks</ref><box>[[38, 464, 97, 497]]</box>" } ]
4
images/62636.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box for the element in the screen to complete the task: <ref>select the first icon adjacent right side of learn japanese</ref>." }, { "from": "gpt", "value": "<ref>select the first icon adjacent right side of learn japanese</ref><box>[[669, 38, 786, 104]]</box>" } ]
5
images/41543.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease identify the area of the element with bounding box that can provide an answer to this question: <ref>click on the third question mark in the page</ref>." }, { "from": "gpt", "value": "<ref>click on the third question mark in the page</ref><box>[[616, 109, 733, 142]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>click on the option having the text share along with an icon</ref>." }, { "from": "gpt", "value": "<ref>click on the option having the text share along with an icon</ref><box>[[804, 145, 1000, 198]]</box>" }, { "from": "human", "value": "For question: <ref>click on continue</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>click on continue</ref><box>[[708, 857, 980, 923]]</box>" }, { "from": "human", "value": "Please identify the location with bounding box that can complete the instruction: <ref>click on 30 comments</ref>." }, { "from": "gpt", "value": "<ref>click on 30 comments</ref><box>[[19, 857, 315, 923]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>click on message icon</ref>." }, { "from": "gpt", "value": "<ref>click on message icon</ref><box>[[883, 38, 1000, 104]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>select the text between id 12</ref>." }, { "from": "gpt", "value": "<ref>select the text between id 12</ref><box>[[498, 375, 559, 405]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on the icon on the top image</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the icon on the top image</ref><box>[[883, 38, 1000, 104]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on play icon above hint</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on play icon above hint</ref><box>[[500, 109, 616, 142]]</box>" } ]
6
images/17200.jpg
540
960
[ { "from": "human", "value": "<image>\nFor question: <ref>click the logo beside fighters</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>click the logo beside fighters</ref><box>[[514, 898, 735, 918]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>click on play icon right to news</ref>." }, { "from": "gpt", "value": "<ref>click on play icon right to news</ref><box>[[596, 856, 653, 889]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>click on share icon</ref>." }, { "from": "gpt", "value": "<ref>click on share icon</ref><box>[[835, 520, 1000, 547]]</box>" } ]
7
images/19024.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the instruction: <ref>go to first image</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>go to first image</ref><box>[[58, 314, 228, 410]]</box>" }, { "from": "human", "value": "Show the bounding box coordinates to click for completing the objective: <ref>click the more options icon</ref>." }, { "from": "gpt", "value": "<ref>click the more options icon</ref><box>[[29, 7, 107, 55]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>select buy at right side of neon set</ref>." }, { "from": "gpt", "value": "<ref>select buy at right side of neon set</ref><box>[[660, 897, 962, 934]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>click on money tag icon of text ice set</ref>." }, { "from": "gpt", "value": "<ref>click on money tag icon of text ice set</ref><box>[[291, 722, 532, 770]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on the buy which is beside fire set</ref>." }, { "from": "gpt", "value": "<ref>click on the buy which is beside fire set</ref><box>[[660, 460, 962, 526]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates that can solve this task: <ref>select the button which is at top right corner of page</ref>." }, { "from": "gpt", "value": "<ref>select the button which is at top right corner of page</ref><box>[[893, 7, 971, 55]]</box>" } ]
8
images/50656.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the instruction: <ref>click on the image icon above restaurants text option</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the image icon above restaurants text option</ref><box>[[68, 747, 202, 822]]</box>" }, { "from": "human", "value": "Please identify the location with bounding box that can complete the instruction: <ref>click the above right 3 dots button</ref>." }, { "from": "gpt", "value": "<ref>click the above right 3 dots button</ref><box>[[883, 38, 1000, 104]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>select hotel icon on the page</ref>." }, { "from": "gpt", "value": "<ref>select hotel icon on the page</ref><box>[[796, 513, 929, 589]]</box>" }, { "from": "human", "value": "Task: <ref>select a icon which is above parking</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select a icon which is above parking</ref><box>[[553, 630, 687, 705]]</box>" }, { "from": "human", "value": "Could you specify the bounding box that is most relevant to the task: <ref>select option movies from the second line</ref>." }, { "from": "gpt", "value": "<ref>select option movies from the second line</ref><box>[[68, 630, 202, 705]]</box>" } ]
9
images/114.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box coordinates that is relevant to the objective: <ref>click the right side height button 6</ref>." }, { "from": "gpt", "value": "<ref>click the right side height button 6</ref><box>[[500, 291, 951, 345]]</box>" } ]
10
images/21137.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nSpecify the bounding box coordinates for completing the instruction: <ref>select the text below the create an account</ref>." }, { "from": "gpt", "value": "<ref>select the text below the create an account</ref><box>[[38, 131, 475, 181]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>select the text input field box which is above the next button</ref>." }, { "from": "gpt", "value": "<ref>select the text input field box which is above the next button</ref><box>[[255, 246, 961, 301]]</box>" } ]
11
images/2415.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nOutput the bounding box of the region to solve the task: <ref>click on the number 1</ref>." }, { "from": "gpt", "value": "<ref>click on the number 1</ref><box>[[25, 123, 74, 183]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>click on the second image in second row</ref>." }, { "from": "gpt", "value": "<ref>click on the second image in second row</ref><box>[[98, 383, 404, 615]]</box>" } ]
12
images/7739.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click on icon on the right side of verbose logging</ref>." }, { "from": "gpt", "value": "<ref>click on icon on the right side of verbose logging</ref><box>[[330, 385, 961, 422]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>click on onoff button which is right side of the automatic crash reporting</ref>." }, { "from": "gpt", "value": "<ref>click on onoff button which is right side of the automatic crash reporting</ref><box>[[504, 534, 961, 571]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates that can solve this task: <ref>click on learn more</ref>." }, { "from": "gpt", "value": "<ref>click on learn more</ref><box>[[38, 249, 231, 296]]</box>" }, { "from": "human", "value": "Task: <ref>click on the copy logs</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the copy logs</ref><box>[[701, 704, 961, 770]]</box>" } ]
13
images/52871.jpg
540
960
[ { "from": "human", "value": "<image>\nCan you provide the click location with bounding box for completing the task: <ref>click on right arrow at the bottom</ref>." }, { "from": "gpt", "value": "<ref>click on right arrow at the bottom</ref><box>[[805, 824, 981, 923]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates that can solve this task: <ref>red color icon below the text december</ref>." }, { "from": "gpt", "value": "<ref>red color icon below the text december</ref><box>[[144, 212, 212, 251]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click the icon left side of dislike icon</ref>." }, { "from": "gpt", "value": "<ref>click the icon left side of dislike icon</ref><box>[[538, 38, 655, 104]]</box>" }, { "from": "human", "value": "Can you provide the click location with bounding box for completing the task: <ref>click on the symbol which is above welcomemail</ref>." }, { "from": "gpt", "value": "<ref>click on the symbol which is above welcomemail</ref><box>[[9, 48, 146, 92]]</box>" }, { "from": "human", "value": "For the instruction: <ref>select the details option</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the details option</ref><box>[[837, 214, 990, 252]]</box>" }, { "from": "human", "value": "What are the precise coordinates of the bounding box where I can click to finalize the instruction: <ref>click on three dots</ref>." }, { "from": "gpt", "value": "<ref>click on three dots</ref><box>[[888, 38, 990, 104]]</box>" } ]
14
images/35663.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nHighlight the click area with bounding box to complete the task: <ref>select the icon left to flight status</ref>." }, { "from": "gpt", "value": "<ref>select the icon left to flight status</ref><box>[[24, 105, 97, 146]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>select the first right scroll in the image</ref>." }, { "from": "gpt", "value": "<ref>select the first right scroll in the image</ref><box>[[953, 192, 975, 210]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the logo below notificationstatus bar</ref>." }, { "from": "gpt", "value": "<ref>click on the logo below notificationstatus bar</ref><box>[[284, 46, 688, 81]]</box>" } ]
15
images/2935.jpg
540
960
[ { "from": "human", "value": "<image>\nFor the operation: <ref>click on the icon on the right side of undisclosed</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the icon on the right side of undisclosed</ref><box>[[892, 766, 990, 820]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on edit button which is next to united states of america</ref>." }, { "from": "gpt", "value": "<ref>click on edit button which is next to united states of america</ref><box>[[892, 697, 990, 753]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>click on delete icon</ref>." }, { "from": "gpt", "value": "<ref>click on delete icon</ref><box>[[874, 320, 990, 386]]</box>" } ]
16
images/22780.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nCan you determine the bounding box coordinates to complete my task: <ref>select the symbol which is to the second right of menu button</ref>." }, { "from": "gpt", "value": "<ref>select the symbol which is to the second right of menu button</ref><box>[[299, 42, 415, 108]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on the icon which is on the left side of more options icon</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the icon which is on the left side of more options icon</ref><box>[[532, 42, 649, 108]]</box>" }, { "from": "human", "value": "Please identify the location with bounding box that can complete the instruction: <ref>click on minus icon</ref>." }, { "from": "gpt", "value": "<ref>click on minus icon</ref><box>[[896, 497, 1000, 556]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>click on the current location icon</ref>." }, { "from": "gpt", "value": "<ref>click on the current location icon</ref><box>[[182, 42, 299, 108]]</box>" } ]
17
images/36625.jpg
540
960
[ { "from": "human", "value": "<image>\nCan you pinpoint the location with bounding box for completing the task: <ref>select the image of police scanner</ref>." }, { "from": "gpt", "value": "<ref>select the image of police scanner</ref><box>[[442, 282, 559, 347]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on the text below the police scanner</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the text below the police scanner</ref><box>[[148, 87, 851, 145]]</box>" } ]
18
images/50898.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for completing the objective: <ref>select more at the bottom of the page</ref>." }, { "from": "gpt", "value": "<ref>select more at the bottom of the page</ref><box>[[800, 853, 999, 933]]</box>" }, { "from": "human", "value": "For the task: <ref>click on wallmart which is below featured stores</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on wallmart which is below featured stores</ref><box>[[14, 655, 371, 720]]</box>" }, { "from": "human", "value": "Specify the location with bounding box to finish the objective: <ref>move to text which is above the text download the free slickdeals app</ref>." }, { "from": "gpt", "value": "<ref>move to text which is above the text download the free slickdeals app</ref><box>[[73, 115, 926, 165]]</box>" } ]
19
images/70031.jpg
540
960
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for completing the objective: <ref>click on the option beside view</ref>." }, { "from": "gpt", "value": "<ref>click on the option beside view</ref><box>[[666, 798, 1000, 864]]</box>" }, { "from": "human", "value": "Please output the bounding box of the region correctly responding to this task: <ref>click on the option which is beside route</ref>." }, { "from": "gpt", "value": "<ref>click on the option which is beside route</ref><box>[[333, 798, 666, 864]]</box>" } ]
20
images/35361.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the region correctly responding to this task: <ref>click on the contact icon under dth beside text field</ref>." }, { "from": "gpt", "value": "<ref>click on the contact icon under dth beside text field</ref><box>[[845, 283, 931, 309]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on the mobile button below the recharge</ref>." }, { "from": "gpt", "value": "<ref>click on the mobile button below the recharge</ref><box>[[73, 183, 500, 242]]</box>" } ]
21
images/16665.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates to solve the task: <ref>go to star icon</ref>." }, { "from": "gpt", "value": "<ref>go to star icon</ref><box>[[926, 109, 975, 136]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>select the last option which is in the green color</ref>." }, { "from": "gpt", "value": "<ref>select the last option which is in the green color</ref><box>[[341, 858, 657, 934]]</box>" }, { "from": "human", "value": "For the task: <ref>click on the right of close</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the right of close</ref><box>[[426, 98, 854, 147]]</box>" } ]
22
images/60410.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the task: <ref>click on menu button</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on menu button</ref><box>[[883, 57, 951, 95]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>go to icon left side of blocked history</ref>." }, { "from": "gpt", "value": "<ref>go to icon left side of blocked history</ref><box>[[38, 517, 97, 550]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on the last plus icon</ref>." }, { "from": "gpt", "value": "<ref>click on the last plus icon</ref><box>[[800, 816, 961, 912]]</box>" } ]
23
images/66371.jpg
540
960
[ { "from": "human", "value": "<image>\nCan you provide the click location with bounding box for completing the task: <ref>click on the first image</ref>." }, { "from": "gpt", "value": "<ref>click on the first image</ref><box>[[12, 192, 255, 327]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>select the browse icon beside comic</ref>." }, { "from": "gpt", "value": "<ref>select the browse icon beside comic</ref><box>[[920, 203, 968, 230]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>click on the button beside art lovers</ref>." }, { "from": "gpt", "value": "<ref>click on the button beside art lovers</ref><box>[[920, 498, 968, 526]]</box>" } ]
24
images/18451.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nCould you specify the bounding box that is most relevant to the task: <ref>click the music icon</ref>." }, { "from": "gpt", "value": "<ref>click the music icon</ref><box>[[4, 805, 174, 901]]</box>" }, { "from": "human", "value": "For the operation: <ref>click the menu icon</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click the menu icon</ref><box>[[24, 43, 101, 87]]</box>" } ]
25
images/62178.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the region correctly responding to this task: <ref>click the first circular shaped image on the left side of the web page</ref>." }, { "from": "gpt", "value": "<ref>click the first circular shaped image on the left side of the web page</ref><box>[[54, 179, 317, 327]]</box>" }, { "from": "human", "value": "For question: <ref>select the first circular shaped image on the right side of the web page</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>select the first circular shaped image on the right side of the web page</ref><box>[[682, 179, 945, 327]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>click on button above hebbars kitchen</ref>." }, { "from": "gpt", "value": "<ref>click on button above hebbars kitchen</ref><box>[[54, 369, 317, 517]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for completing the objective: <ref>click on the button under faking news</ref>." }, { "from": "gpt", "value": "<ref>click on the button under faking news</ref><box>[[682, 560, 945, 707]]</box>" }, { "from": "human", "value": "For the task: <ref>click on the button having a text faking news</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the button having a text faking news</ref><box>[[682, 369, 945, 517]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>click on the image having filmfare option</ref>." }, { "from": "gpt", "value": "<ref>click on the image having filmfare option</ref><box>[[682, 179, 945, 327]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box that can finalize the instruction: <ref>click on the button that having a text comedy munch</ref>." }, { "from": "gpt", "value": "<ref>click on the button that having a text comedy munch</ref><box>[[54, 369, 317, 517]]</box>" }, { "from": "human", "value": "Show the bounding box coordinates to click for completing the objective: <ref>click on the button having a text tbs planet</ref>." }, { "from": "gpt", "value": "<ref>click on the button having a text tbs planet</ref><box>[[682, 750, 945, 863]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>click on the button that having a text filmfare</ref>." }, { "from": "gpt", "value": "<ref>click on the button that having a text filmfare</ref><box>[[682, 179, 945, 327]]</box>" }, { "from": "human", "value": "Task: <ref>click on the button that having a text fever fm</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the button that having a text fever fm</ref><box>[[368, 560, 631, 707]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>click on the button that having a text breaking</ref>." }, { "from": "gpt", "value": "<ref>click on the button that having a text breaking</ref><box>[[368, 750, 631, 863]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates that can solve this task: <ref>click on the button that having a text fever fm</ref>." }, { "from": "gpt", "value": "<ref>click on the button that having a text fever fm</ref><box>[[368, 560, 631, 707]]</box>" }, { "from": "human", "value": "For task: <ref>click on the button that having a text hebbars kitchen</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>click on the button that having a text hebbars kitchen</ref><box>[[54, 560, 317, 707]]</box>" } ]
26
images/7724.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box to solve the task: <ref>click on image right to 12 pm</ref>." }, { "from": "gpt", "value": "<ref>click on image right to 12 pm</ref><box>[[147, 826, 220, 875]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>select the symbol right to 11 am</ref>." }, { "from": "gpt", "value": "<ref>select the symbol right to 11 am</ref><box>[[149, 744, 221, 798]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>click on the button which is to the left of settings button</ref>." }, { "from": "gpt", "value": "<ref>click on the button which is to the left of settings button</ref><box>[[490, 101, 653, 149]]</box>" } ]
27
images/29643.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the operation: <ref>select 1 line text above acura</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select 1 line text above acura</ref><box>[[312, 829, 1000, 866]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the image tigers</ref>." }, { "from": "gpt", "value": "<ref>click on the image tigers</ref><box>[[19, 687, 311, 796]]</box>" } ]
28
images/35089.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nCould you specify the bounding box that is most relevant to the task: <ref>click on the button which is next to button</ref>." }, { "from": "gpt", "value": "<ref>click on the button which is next to button</ref><box>[[600, 868, 799, 934]]</box>" }, { "from": "human", "value": "Can you determine the bounding box coordinates to complete my task: <ref>click on the button which is left side of the button</ref>." }, { "from": "gpt", "value": "<ref>click on the button which is left side of the button</ref><box>[[201, 868, 400, 934]]</box>" } ]
29
images/18861.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor task: <ref>go to the third image from the top of the page</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>go to the third image from the top of the page</ref><box>[[3, 285, 149, 366]]</box>" }, { "from": "human", "value": "Could you specify the bounding box that is most relevant to the task: <ref>click the youtube logo on the web page</ref>." }, { "from": "gpt", "value": "<ref>click the youtube logo on the web page</ref><box>[[268, 34, 396, 102]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>select the image from bottom left side of the web page</ref>." }, { "from": "gpt", "value": "<ref>select the image from bottom left side of the web page</ref><box>[[3, 460, 149, 541]]</box>" }, { "from": "human", "value": "Can you provide the click location with bounding box for completing the task: <ref>select the first image from the top left side of the web page</ref>." }, { "from": "gpt", "value": "<ref>select the first image from the top left side of the web page</ref><box>[[3, 110, 149, 191]]</box>" } ]
30
images/21959.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates that can solve this task: <ref>click on the second blog</ref>." }, { "from": "gpt", "value": "<ref>click on the second blog</ref><box>[[19, 292, 980, 443]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>select the first block under the menu bar</ref>." }, { "from": "gpt", "value": "<ref>select the first block under the menu bar</ref><box>[[19, 120, 980, 270]]</box>" } ]
31
images/47615.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for solving the task: <ref>click on the back arrow in top left corner</ref>." }, { "from": "gpt", "value": "<ref>click on the back arrow in top left corner</ref><box>[[34, 62, 116, 84]]</box>" }, { "from": "human", "value": "For task: <ref>click on the text below ciudad</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>click on the text below ciudad</ref><box>[[34, 647, 150, 666]]</box>" } ]
32
images/65160.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhat is the bounding box coordinates that is most relevant to this task: <ref>select icon of under armour</ref>." }, { "from": "gpt", "value": "<ref>select icon of under armour</ref><box>[[38, 579, 174, 655]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>select the four different color box which is besides the living social</ref>." }, { "from": "gpt", "value": "<ref>select the four different color box which is besides the living social</ref><box>[[38, 877, 174, 934]]</box>" } ]
33
images/61302.jpg
540
960
[ { "from": "human", "value": "<image>\nHighlight the area with bounding box that I can click to execute the task: <ref>click on search icon next below 3 vertical dots at the top right corner of the page</ref>." }, { "from": "gpt", "value": "<ref>click on search icon next below 3 vertical dots at the top right corner of the page</ref><box>[[881, 150, 955, 200]]</box>" }, { "from": "human", "value": "For the task: <ref>click on map button which is at bottom right corner</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on map button which is at bottom right corner</ref><box>[[670, 873, 990, 929]]</box>" } ]
34
images/16994.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nShow me the bounding box coordinates that can provide an answer to the operation: <ref>select the checkbox just right to flickr</ref>." }, { "from": "gpt", "value": "<ref>select the checkbox just right to flickr</ref><box>[[839, 99, 917, 143]]</box>" } ]
35
images/12880.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nTask: <ref>select the icon which is before cash</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select the icon which is before cash</ref><box>[[38, 311, 97, 344]]</box>" } ]
36
images/38022.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box for the element in the screen to complete the task: <ref>select the text gallery below downloads</ref>." }, { "from": "gpt", "value": "<ref>select the text gallery below downloads</ref><box>[[10, 360, 495, 601]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>click on video icon in right of the page</ref>." }, { "from": "gpt", "value": "<ref>click on video icon in right of the page</ref><box>[[902, 311, 961, 344]]</box>" }, { "from": "human", "value": "Task: <ref>option below the 3 dotted vertical line icon</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>option below the 3 dotted vertical line icon</ref><box>[[504, 115, 990, 355]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the gallery icon</ref>." }, { "from": "gpt", "value": "<ref>click on the gallery icon</ref><box>[[38, 346, 97, 401]]</box>" } ]
37
images/33229.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click on the search icon</ref>." }, { "from": "gpt", "value": "<ref>click on the search icon</ref><box>[[863, 38, 1000, 104]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates that can solve this task: <ref>select fork icon</ref>." }, { "from": "gpt", "value": "<ref>select fork icon</ref><box>[[824, 759, 961, 835]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on the third plus icon</ref>." }, { "from": "gpt", "value": "<ref>click on the third plus icon</ref><box>[[38, 784, 97, 852]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click on the fourth add button below ingredients required</ref>." }, { "from": "gpt", "value": "<ref>click on the fourth add button below ingredients required</ref><box>[[38, 852, 97, 934]]</box>" } ]
38
images/25689.jpg
540
960
[ { "from": "human", "value": "<image>\nCould you specify the bounding box that is most relevant to the task: <ref>click on the image which is just above the close button</ref>." }, { "from": "gpt", "value": "<ref>click on the image which is just above the close button</ref><box>[[248, 463, 751, 626]]</box>" }, { "from": "human", "value": "Please identify the area of the element with bounding box that can provide an answer to this question: <ref>select the option icon which is at the left side corner</ref>." }, { "from": "gpt", "value": "<ref>select the option icon which is at the left side corner</ref><box>[[12, 39, 172, 100]]</box>" } ]
39
images/34280.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the task: <ref>select the image below review reference which consists of three options</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the image below review reference which consists of three options</ref><box>[[49, 146, 951, 766]]</box>" }, { "from": "human", "value": "For the instruction: <ref>select the second icon which is under the text review references</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the second icon which is under the text review references</ref><box>[[501, 199, 642, 279]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>select the speaker symbol which is on the right side of the screen</ref>." }, { "from": "gpt", "value": "<ref>select the speaker symbol which is on the right side of the screen</ref><box>[[868, 832, 1000, 905]]</box>" } ]
40
images/65566.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor question: <ref>click on the dragon image</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>click on the dragon image</ref><box>[[4, 400, 165, 490]]</box>" }, { "from": "human", "value": "For question: <ref>click on image left to text scene00</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>click on image left to text scene00</ref><box>[[4, 218, 165, 308]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on the symbol left to search</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the symbol left to search</ref><box>[[591, 32, 727, 98]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>click on search icon</ref>." }, { "from": "gpt", "value": "<ref>click on search icon</ref><box>[[727, 32, 863, 98]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>click on play button</ref>." }, { "from": "gpt", "value": "<ref>click on play button</ref><box>[[42, 109, 120, 153]]</box>" } ]
41
images/69224.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease identify the location with bounding box that can complete the instruction: <ref>select the text field which is below mail on the page</ref>." }, { "from": "gpt", "value": "<ref>select the text field which is below mail on the page</ref><box>[[38, 526, 961, 580]]</box>" }, { "from": "human", "value": "Task: <ref>select the icon which is to the left side of edit teacher option</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select the icon which is to the left side of edit teacher option</ref><box>[[29, 43, 107, 87]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>click on save icon</ref>." }, { "from": "gpt", "value": "<ref>click on save icon</ref><box>[[863, 32, 1000, 98]]</box>" }, { "from": "human", "value": "Please output the bounding box of the region correctly responding to this task: <ref>select the button which is below office</ref>." }, { "from": "gpt", "value": "<ref>select the button which is below office</ref><box>[[38, 226, 961, 279]]</box>" } ]
42
images/51055.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box that can finalize the instruction: <ref>select filipino on the page</ref>." }, { "from": "gpt", "value": "<ref>select filipino on the page</ref><box>[[38, 349, 961, 393]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>select the swedish option</ref>." }, { "from": "gpt", "value": "<ref>select the swedish option</ref><box>[[38, 568, 961, 612]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>select the text which is above the text swedish</ref>." }, { "from": "gpt", "value": "<ref>select the text which is above the text swedish</ref><box>[[38, 524, 961, 568]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>select the text which is immediately below danish</ref>." }, { "from": "gpt", "value": "<ref>select the text which is immediately below danish</ref><box>[[38, 656, 961, 699]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click on italiano</ref>." }, { "from": "gpt", "value": "<ref>click on italiano</ref><box>[[38, 262, 961, 306]]</box>" }, { "from": "human", "value": "For task: <ref>select espanol option</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>select espanol option</ref><box>[[38, 306, 961, 349]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>click on done</ref>." }, { "from": "gpt", "value": "<ref>click on done</ref><box>[[38, 754, 961, 819]]</box>" } ]
43
images/42255.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the instruction: <ref>select the image above fan</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the image above fan</ref><box>[[472, 875, 526, 906]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>icon before cool text below 70</ref>." }, { "from": "gpt", "value": "<ref>icon before cool text below 70</ref><box>[[73, 228, 121, 255]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>icon above the text called system</ref>." }, { "from": "gpt", "value": "<ref>icon above the text called system</ref><box>[[272, 875, 326, 906]]</box>" } ]
44
images/18134.jpg
540
960
[ { "from": "human", "value": "<image>\nCan you determine the bounding box coordinates to complete my task: <ref>select the last four alphabets in the second row of the key board</ref>." }, { "from": "gpt", "value": "<ref>select the last four alphabets in the second row of the key board</ref><box>[[511, 664, 903, 773]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>select the alphabets from y to o in the first row of the keyboard</ref>." }, { "from": "gpt", "value": "<ref>select the alphabets from y to o in the first row of the keyboard</ref><box>[[511, 541, 903, 651]]</box>" } ]
45
images/67053.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhat is the bounding box coordinates that is most relevant to this task: <ref>click on the first image</ref>." }, { "from": "gpt", "value": "<ref>click on the first image</ref><box>[[829, 157, 975, 291]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>select the 2nd picture from the top</ref>." }, { "from": "gpt", "value": "<ref>select the 2nd picture from the top</ref><box>[[829, 296, 975, 416]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>select 4th image which is below scienc at the right side of the page</ref>." }, { "from": "gpt", "value": "<ref>select 4th image which is below scienc at the right side of the page</ref><box>[[829, 545, 975, 665]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the image right to the text mystery space capsule confounds arizonans</ref>." }, { "from": "gpt", "value": "<ref>click on the image right to the text mystery space capsule confounds arizonans</ref><box>[[829, 794, 975, 866]]</box>" } ]
46
images/9448.jpg
540
960
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for solving the task: <ref>select the next button which is on the bottom right of the page</ref>." }, { "from": "gpt", "value": "<ref>select the next button which is on the bottom right of the page</ref><box>[[787, 861, 1000, 931]]</box>" } ]
47
images/688.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box coordinates that is relevant to the objective: <ref>select the text box which says take a shortcut</ref>." }, { "from": "gpt", "value": "<ref>select the text box which says take a shortcut</ref><box>[[302, 629, 697, 694]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>click on logo above exceptions files</ref>." }, { "from": "gpt", "value": "<ref>click on logo above exceptions files</ref><box>[[426, 735, 573, 817]]</box>" }, { "from": "human", "value": "Please output the bounding box of the region correctly responding to this task: <ref>select the symbol above control structures</ref>." }, { "from": "gpt", "value": "<ref>select the symbol above control structures</ref><box>[[176, 440, 323, 522]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>select the forward symbol option above basic concepts</ref>." }, { "from": "gpt", "value": "<ref>select the forward symbol option above basic concepts</ref><box>[[426, 144, 573, 227]]</box>" } ]
48
images/70400.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box to solve the task: <ref>select the check box that is to the right of hide warning bar</ref>." }, { "from": "gpt", "value": "<ref>select the check box that is to the right of hide warning bar</ref><box>[[839, 562, 917, 606]]</box>" }, { "from": "human", "value": "For task: <ref>the second checkbox from the top of the page</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>the second checkbox from the top of the page</ref><box>[[839, 651, 917, 694]]</box>" } ]
49
images/3800.jpg
540
960
[ { "from": "human", "value": "<image>\nPlease identify the area of the element with bounding box that can provide an answer to this question: <ref>select the text box which says password</ref>." }, { "from": "gpt", "value": "<ref>select the text box which says password</ref><box>[[37, 318, 962, 375]]</box>" }, { "from": "human", "value": "For question: <ref>sign in</ref>, locate the bounding box of the element in the image that holds the key to this question." }, { "from": "gpt", "value": "<ref>sign in</ref><box>[[33, 449, 966, 515]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>click on mylowes logo</ref>." }, { "from": "gpt", "value": "<ref>click on mylowes logo</ref><box>[[14, 48, 170, 82]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>click on the shop icon</ref>." }, { "from": "gpt", "value": "<ref>click on the shop icon</ref><box>[[270, 869, 329, 902]]</box>" }, { "from": "human", "value": "Task: <ref>select the preferences icon</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select the preferences icon</ref><box>[[688, 755, 811, 809]]</box>" } ]
50
images/64302.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhat is the bounding box coordinates that is most relevant to this task: <ref>click on icon beside share</ref>." }, { "from": "gpt", "value": "<ref>click on icon beside share</ref><box>[[883, 38, 1000, 104]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>select the icon top center of the page</ref>." }, { "from": "gpt", "value": "<ref>select the icon top center of the page</ref><box>[[441, 109, 558, 141]]</box>" } ]
51
images/38749.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates to solve the task: <ref>click on the add icon</ref>." }, { "from": "gpt", "value": "<ref>click on the add icon</ref><box>[[649, 32, 766, 104]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>select add option which is before save option</ref>." }, { "from": "gpt", "value": "<ref>select add option which is before save option</ref><box>[[657, 51, 793, 95]]</box>" }, { "from": "human", "value": "Please identify the area of the element with bounding box that can provide an answer to this question: <ref>select the multiple content which is below green dotenter card</ref>." }, { "from": "gpt", "value": "<ref>select the multiple content which is below green dotenter card</ref><box>[[210, 396, 793, 615]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box that can finalize the instruction: <ref>click on the wrong option to the right of the text green dot i enter card</ref>." }, { "from": "gpt", "value": "<ref>click on the wrong option to the right of the text green dot i enter card</ref><box>[[657, 352, 793, 396]]</box>" } ]
52
images/46218.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nOutput the bounding box of the element in the image that directly relates to solving this question: <ref>icon before ideas text</ref>." }, { "from": "gpt", "value": "<ref>icon before ideas text</ref><box>[[774, 882, 808, 904]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>click on the icon which is to the right from the bubble</ref>." }, { "from": "gpt", "value": "<ref>click on the icon which is to the right from the bubble</ref><box>[[637, 47, 790, 94]]</box>" } ]
53
images/45600.jpg
540
960
[ { "from": "human", "value": "<image>\nCan you pinpoint the location with bounding box for completing the task: <ref>click the arrow left to suggested retail</ref>." }, { "from": "gpt", "value": "<ref>click the arrow left to suggested retail</ref><box>[[16, 376, 42, 403]]</box>" }, { "from": "human", "value": "Can you determine the bounding box coordinates to complete my task: <ref>click on icon which is left of tradein fair</ref>." }, { "from": "gpt", "value": "<ref>click on icon which is left of tradein fair</ref><box>[[16, 633, 42, 661]]</box>" } ]
54
images/36006.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box that can finalize the instruction: <ref>select the image on the top right corner</ref>." }, { "from": "gpt", "value": "<ref>select the image on the top right corner</ref><box>[[883, 32, 1000, 101]]</box>" }, { "from": "human", "value": "For the task: <ref>click on the arrow symbol which is on the left side of appcrawler4gmailcom</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the arrow symbol which is on the left side of appcrawler4gmailcom</ref><box>[[685, 796, 801, 862]]</box>" } ]
55
images/57253.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nOutput the bounding box of the region to solve the task: <ref>go to the first icon from bottom</ref>." }, { "from": "gpt", "value": "<ref>go to the first icon from bottom</ref><box>[[38, 866, 161, 931]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>click on the icon bottom of right corner</ref>." }, { "from": "gpt", "value": "<ref>click on the icon bottom of right corner</ref><box>[[838, 866, 961, 931]]</box>" } ]
56
images/21553.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>select the icon which is left side of the mcdelivery</ref>." }, { "from": "gpt", "value": "<ref>select the icon which is left side of the mcdelivery</ref><box>[[68, 43, 146, 87]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>select the icon which is left side of the mcdelivery</ref>." }, { "from": "gpt", "value": "<ref>select the icon which is left side of the mcdelivery</ref><box>[[68, 43, 146, 87]]</box>" } ]
57
images/9416.jpg
540
960
[ { "from": "human", "value": "<image>\nFor the operation: <ref>below the password option</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>below the password option</ref><box>[[20, 694, 98, 738]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click on icon next to contacts</ref>." }, { "from": "gpt", "value": "<ref>click on icon next to contacts</ref><box>[[20, 552, 98, 595]]</box>" }, { "from": "human", "value": "For the task: <ref>click the fourth icon from the left top of the page</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click the fourth icon from the left top of the page</ref><box>[[20, 337, 98, 381]]</box>" } ]
58
images/60295.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nSpecify the location with bounding box to finish the objective: <ref>click on second image from bottom</ref>." }, { "from": "gpt", "value": "<ref>click on second image from bottom</ref><box>[[449, 552, 812, 757]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the home button at top left</ref>." }, { "from": "gpt", "value": "<ref>click on the home button at top left</ref><box>[[37, 28, 104, 66]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>select the text which is to the right of place my face</ref>." }, { "from": "gpt", "value": "<ref>select the text which is to the right of place my face</ref><box>[[806, 24, 987, 71]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>tag the logo mentioned at center top of the page</ref>." }, { "from": "gpt", "value": "<ref>tag the logo mentioned at center top of the page</ref><box>[[341, 11, 657, 83]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>click on misc symbol</ref>." }, { "from": "gpt", "value": "<ref>click on misc symbol</ref><box>[[57, 423, 190, 499]]</box>" } ]
59
images/52924.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click on the chat icon to the top right corner</ref>." }, { "from": "gpt", "value": "<ref>click on the chat icon to the top right corner</ref><box>[[917, 43, 980, 77]]</box>" }, { "from": "human", "value": "Task: <ref>click on the text join more communities along with the search button</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the text join more communities along with the search button</ref><box>[[19, 655, 859, 702]]</box>" }, { "from": "human", "value": "For task: <ref>click the latest icon</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>click the latest icon</ref><box>[[822, 107, 865, 131]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>click on mini image which is above crybabies</ref>." }, { "from": "gpt", "value": "<ref>click on mini image which is above crybabies</ref><box>[[437, 713, 535, 767]]</box>" } ]
60
images/19963.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nShow me the bounding box coordinates that can provide an answer to the operation: <ref>click on xkill</ref>." }, { "from": "gpt", "value": "<ref>click on xkill</ref><box>[[19, 811, 137, 841]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>click on the text clear</ref>." }, { "from": "gpt", "value": "<ref>click on the text clear</ref><box>[[19, 434, 154, 464]]</box>" } ]
61
images/9543.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nCan you determine the bounding box coordinates to complete my task: <ref>select option privacy which is on the right corner of the page</ref>." }, { "from": "gpt", "value": "<ref>select option privacy which is on the right corner of the page</ref><box>[[829, 675, 1000, 737]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>click on the drop down which is on the right side of entertainment</ref>." }, { "from": "gpt", "value": "<ref>click on the drop down which is on the right side of entertainment</ref><box>[[679, 773, 829, 786]]</box>" } ]
62
images/48926.jpg
540
960
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click on the email option in the required field</ref>." }, { "from": "gpt", "value": "<ref>click on the email option in the required field</ref><box>[[12, 437, 987, 524]]</box>" } ]
63
images/29257.jpg
540
960
[ { "from": "human", "value": "<image>\nOutput the bounding box of the region to solve the task: <ref>select the rotation icon</ref>." }, { "from": "gpt", "value": "<ref>select the rotation icon</ref><box>[[472, 858, 550, 902]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click on the position icon</ref>." }, { "from": "gpt", "value": "<ref>click on the position icon</ref><box>[[325, 858, 403, 902]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>select the left scroll</ref>." }, { "from": "gpt", "value": "<ref>select the left scroll</ref><box>[[48, 208, 203, 273]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>select the right scroll button</ref>." }, { "from": "gpt", "value": "<ref>select the right scroll button</ref><box>[[205, 208, 361, 273]]</box>" } ]
64
images/200.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nOutput the bounding box of the region to solve the task: <ref>select the more options icon</ref>." }, { "from": "gpt", "value": "<ref>select the more options icon</ref><box>[[728, 32, 1000, 98]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>select the icon which is above home option</ref>." }, { "from": "gpt", "value": "<ref>select the icon which is above home option</ref><box>[[21, 42, 143, 110]]</box>" } ]
65
images/47622.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease identify the location with bounding box that can complete the instruction: <ref>click on champaign il </ref>." }, { "from": "gpt", "value": "<ref>click on champaign il </ref><box>[[34, 133, 357, 167]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>click the left arrow icon right to lluvia ligera</ref>." }, { "from": "gpt", "value": "<ref>click the left arrow icon right to lluvia ligera</ref><box>[[408, 362, 481, 402]]</box>" } ]
66
images/2768.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the operation: <ref>select the k button</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select the k button</ref><box>[[431, 128, 567, 192]]</box>" } ]
67
images/53607.jpg
540
960
[ { "from": "human", "value": "<image>\nInstruction: <ref>click on the online option</ref>, output the bounding box of the region in the screen that can complete the task." }, { "from": "gpt", "value": "<ref>click on the online option</ref><box>[[262, 122, 500, 170]]</box>" }, { "from": "human", "value": "For the task: <ref>click on the icon just left to estimate price</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the icon just left to estimate price</ref><box>[[12, 43, 85, 84]]</box>" }, { "from": "human", "value": "For the operation: <ref>select more</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select more</ref><box>[[800, 872, 1000, 934]]</box>" } ]
68
images/13087.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhat is the bounding box coordinates that is most relevant to this task: <ref>click on more button in second image</ref>." }, { "from": "gpt", "value": "<ref>click on more button in second image</ref><box>[[917, 755, 975, 788]]</box>" } ]
69
images/14778.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nShow me the bounding box coordinates that can provide an answer to the operation: <ref>click on second image</ref>." }, { "from": "gpt", "value": "<ref>click on second image</ref><box>[[24, 306, 364, 497]]</box>" }, { "from": "human", "value": "Task: <ref>click on sort by icon</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on sort by icon</ref><box>[[404, 883, 462, 916]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>click on the third image from top</ref>." }, { "from": "gpt", "value": "<ref>click on the third image from top</ref><box>[[24, 514, 364, 705]]</box>" }, { "from": "human", "value": "Show the bounding box coordinates to click for completing the objective: <ref>select the icons right to search field</ref>." }, { "from": "gpt", "value": "<ref>select the icons right to search field</ref><box>[[766, 43, 961, 98]]</box>" }, { "from": "human", "value": "Specify the location with bounding box to finish the objective: <ref>click on second image left to the pickwick hotel</ref>." }, { "from": "gpt", "value": "<ref>click on second image left to the pickwick hotel</ref><box>[[24, 306, 364, 497]]</box>" } ]
70
images/60222.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates to solve the task: <ref>click on more icon options</ref>." }, { "from": "gpt", "value": "<ref>click on more icon options</ref><box>[[902, 38, 1000, 104]]</box>" }, { "from": "human", "value": "For task: <ref>click on the image which is left to ty</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>click on the image which is left to ty</ref><box>[[38, 159, 136, 214]]</box>" }, { "from": "human", "value": "For the operation: <ref>click on first comment profile picture</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on first comment profile picture</ref><box>[[38, 318, 136, 372]]</box>" } ]
71
images/47840.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates to solve the task: <ref>the third check box of the page</ref>." }, { "from": "gpt", "value": "<ref>the third check box of the page</ref><box>[[38, 397, 87, 424]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>checkbox icon left to the text pastry chef services</ref>." }, { "from": "gpt", "value": "<ref>checkbox icon left to the text pastry chef services</ref><box>[[38, 536, 87, 564]]</box>" } ]
72
images/10805.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box coordinates that is relevant to the objective: <ref>click on heart symbol which is on right side of super smash bros</ref>." }, { "from": "gpt", "value": "<ref>click on heart symbol which is on right side of super smash bros</ref><box>[[824, 700, 961, 755]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>click the box beside league</ref>." }, { "from": "gpt", "value": "<ref>click the box beside league</ref><box>[[38, 315, 136, 370]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>click the heart icon at right side of dota 2</ref>." }, { "from": "gpt", "value": "<ref>click the heart icon at right side of dota 2</ref><box>[[824, 392, 961, 447]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>select favorite icon which is after call of duty</ref>." }, { "from": "gpt", "value": "<ref>select favorite icon which is after call of duty</ref><box>[[824, 623, 961, 678]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click the icon at left side of the heroes of the storm</ref>." }, { "from": "gpt", "value": "<ref>click the icon at left side of the heroes of the storm</ref><box>[[38, 854, 136, 908]]</box>" } ]
73
images/71864.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box for the element in the screen to complete the task: <ref>enter left arrow</ref>." }, { "from": "gpt", "value": "<ref>enter left arrow</ref><box>[[55, 51, 116, 85]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>click on top left corner button</ref>." }, { "from": "gpt", "value": "<ref>click on top left corner button</ref><box>[[37, 34, 151, 102]]</box>" }, { "from": "human", "value": "Please identify the location with bounding box that can complete the instruction: <ref>select the eye button above the find passwords</ref>." }, { "from": "gpt", "value": "<ref>select the eye button above the find passwords</ref><box>[[878, 224, 956, 268]]</box>" }, { "from": "human", "value": "What is the bounding box coordinates that is most relevant to this task: <ref>select the icon mention in button at bottom center of the page</ref>." }, { "from": "gpt", "value": "<ref>select the icon mention in button at bottom center of the page</ref><box>[[397, 792, 474, 835]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>select the text which is to the right side of the back arrow button</ref>." }, { "from": "gpt", "value": "<ref>select the text which is to the right side of the back arrow button</ref><box>[[187, 52, 812, 84]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>click on orange button</ref>." }, { "from": "gpt", "value": "<ref>click on orange button</ref><box>[[43, 363, 956, 431]]</box>" } ]
74
images/41125.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nOutput the bounding box of the region to solve the task: <ref>click on message icon at top right</ref>." }, { "from": "gpt", "value": "<ref>click on message icon at top right</ref><box>[[865, 60, 975, 105]]</box>" }, { "from": "human", "value": "Show the bounding box coordinates to click for completing the objective: <ref>no tagging available</ref>." }, { "from": "gpt", "value": "<ref>no tagging available</ref><box>[[0, 506, 1000, 533]]</box>" } ]
75
images/59972.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the task: <ref>click on the second image from left side</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the second image from left side</ref><box>[[632, 246, 749, 311]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>click on the fifth button above the text intensity</ref>." }, { "from": "gpt", "value": "<ref>click on the fifth button above the text intensity</ref><box>[[823, 246, 939, 311]]</box>" }, { "from": "human", "value": "Can you provide the click location with bounding box for completing the task: <ref>select the icon which is left side of the set auto timer</ref>." }, { "from": "gpt", "value": "<ref>select the icon which is left side of the set auto timer</ref><box>[[60, 686, 118, 719]]</box>" } ]
76
images/68301.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for solving the task: <ref>click on cancel button</ref>." }, { "from": "gpt", "value": "<ref>click on cancel button</ref><box>[[718, 43, 805, 93]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>click on the button at the top right corner of the page</ref>." }, { "from": "gpt", "value": "<ref>click on the button at the top right corner of the page</ref><box>[[854, 46, 971, 111]]</box>" } ]
77
images/42309.jpg
540
960
[ { "from": "human", "value": "<image>\nProvide the bounding box coordinates to solve the task: <ref>select the date 9 of january</ref>." }, { "from": "gpt", "value": "<ref>select the date 9 of january</ref><box>[[27, 608, 157, 659]]</box>" }, { "from": "human", "value": "For the instruction: <ref>select the date 21 of january</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the date 21 of january</ref><box>[[707, 662, 837, 714]]</box>" }, { "from": "human", "value": "Please identify the area of the element with bounding box that can provide an answer to this question: <ref>click the number 27 which is on tuesday</ref>." }, { "from": "gpt", "value": "<ref>click the number 27 which is on tuesday</ref><box>[[162, 355, 294, 407]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>select the date 3 from month january 2017</ref>." }, { "from": "gpt", "value": "<ref>select the date 3 from month january 2017</ref><box>[[162, 553, 294, 605]]</box>" } ]
78
images/68796.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nCould you specify the bounding box that is most relevant to the task: <ref>click on camera icon</ref>." }, { "from": "gpt", "value": "<ref>click on camera icon</ref><box>[[422, 763, 577, 844]]</box>" }, { "from": "human", "value": "Could you specify the bounding box that is most relevant to the task: <ref>go to the fourth smiley of the page</ref>." }, { "from": "gpt", "value": "<ref>go to the fourth smiley of the page</ref><box>[[399, 438, 524, 508]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box that can finalize the instruction: <ref>select the image above next</ref>." }, { "from": "gpt", "value": "<ref>select the image above next</ref><box>[[38, 580, 961, 844]]</box>" }, { "from": "human", "value": "Can you determine the bounding box coordinates to complete my task: <ref>select the right corner emoji</ref>." }, { "from": "gpt", "value": "<ref>select the right corner emoji</ref><box>[[777, 438, 904, 508]]</box>" }, { "from": "human", "value": "Task: <ref>select the icon above no map available</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>select the icon above no map available</ref><box>[[418, 144, 580, 235]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>choose the first emoji above add a note</ref>." }, { "from": "gpt", "value": "<ref>choose the first emoji above add a note</ref><box>[[19, 438, 146, 508]]</box>" } ]
79
images/61215.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nSpecify the bounding box coordinates for completing the instruction: <ref>click on icon left to more apps</ref>." }, { "from": "gpt", "value": "<ref>click on icon left to more apps</ref><box>[[24, 558, 97, 585]]</box>" }, { "from": "human", "value": "What are the precise coordinates of the bounding box where I can click to finalize the instruction: <ref>click on logo at bottom left corner</ref>." }, { "from": "gpt", "value": "<ref>click on logo at bottom left corner</ref><box>[[49, 932, 388, 962]]</box>" }, { "from": "human", "value": "For the task: <ref>go to left of wins</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>go to left of wins</ref><box>[[24, 280, 97, 307]]</box>" }, { "from": "human", "value": "For the operation: <ref>go to left of history</ref>, output the bounding box of the region in the image that can complete the task." }, { "from": "gpt", "value": "<ref>go to left of history</ref><box>[[24, 349, 97, 377]]</box>" } ]
80
images/25578.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click the button on the top right corner of the web page</ref>." }, { "from": "gpt", "value": "<ref>click the button on the top right corner of the web page</ref><box>[[902, 32, 1000, 98]]</box>" }, { "from": "human", "value": "For the instruction: <ref>click the drop down button left to at right corner bottom</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click the drop down button left to at right corner bottom</ref><box>[[664, 868, 898, 934]]</box>" }, { "from": "human", "value": "Can you provide the click location with bounding box for completing the task: <ref>click the drop down button left to at right corner bottom of the page</ref>." }, { "from": "gpt", "value": "<ref>click the drop down button left to at right corner bottom of the page</ref><box>[[751, 868, 810, 934]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>click on grid view icon below search bar</ref>." }, { "from": "gpt", "value": "<ref>click on grid view icon below search bar</ref><box>[[19, 885, 77, 918]]</box>" }, { "from": "human", "value": "For the instruction: <ref>click on the icon in the bottom left corner</ref>, output the bounding box for the region in the screen that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the icon in the bottom left corner</ref><box>[[902, 868, 1000, 934]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>move to star symbol beside the text new tab page</ref>." }, { "from": "gpt", "value": "<ref>move to star symbol beside the text new tab page</ref><box>[[10, 32, 107, 98]]</box>" } ]
81
images/1518.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box that can finalize the instruction: <ref>click on the icon to the right side of 000</ref>." }, { "from": "gpt", "value": "<ref>click on the icon to the right side of 000</ref><box>[[932, 290, 990, 322]]</box>" }, { "from": "human", "value": "Provide the bounding box coordinates to solve the task: <ref>the first icon right to alcodroid at the top of the page</ref>." }, { "from": "gpt", "value": "<ref>the first icon right to alcodroid at the top of the page</ref><box>[[669, 38, 786, 104]]</box>" } ]
82
images/15860.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the operation: <ref>click on the icon left to search icon</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the icon left to search icon</ref><box>[[71, 879, 129, 912]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>move to first icon at bottom right</ref>." }, { "from": "gpt", "value": "<ref>move to first icon at bottom right</ref><box>[[871, 879, 929, 912]]</box>" }, { "from": "human", "value": "For the task: <ref>click the button on the right next to the button on the web page</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click the button on the right next to the button on the web page</ref><box>[[671, 879, 729, 912]]</box>" } ]
83
images/11425.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>click on the more options icon which is on the top right corner</ref>." }, { "from": "gpt", "value": "<ref>click on the more options icon which is on the top right corner</ref><box>[[902, 41, 1000, 106]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>select the first frame in third row</ref>." }, { "from": "gpt", "value": "<ref>select the first frame in third row</ref><box>[[38, 494, 500, 675]]</box>" } ]
84
images/27607.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor the task: <ref>click on skip option</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on skip option</ref><box>[[453, 679, 546, 767]]</box>" }, { "from": "human", "value": "Specify the location with bounding box to finish the objective: <ref>click on the wrong option</ref>." }, { "from": "gpt", "value": "<ref>click on the wrong option</ref><box>[[140, 679, 296, 767]]</box>" }, { "from": "human", "value": "Highlight the area with bounding box that I can click to execute the task: <ref>select the text which is at the bottom of the page</ref>." }, { "from": "gpt", "value": "<ref>select the text which is at the bottom of the page</ref><box>[[58, 868, 941, 934]]</box>" } ]
85
images/46575.jpg
540
960
[ { "from": "human", "value": "<image>\nPlease identify the location with bounding box that can complete the instruction: <ref>select more</ref>." }, { "from": "gpt", "value": "<ref>select more</ref><box>[[792, 846, 1000, 934]]</box>" }, { "from": "human", "value": "Task: <ref>button which is right to lb</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>button which is right to lb</ref><box>[[572, 121, 718, 177]]</box>" }, { "from": "human", "value": "Indicate the precise location with bounding box that can solve the problem: <ref>click on baby icon</ref>." }, { "from": "gpt", "value": "<ref>click on baby icon</ref><box>[[448, 855, 550, 912]]</box>" }, { "from": "human", "value": "Indicate the location with bounding box to solve the task: <ref>click on video option beside today option</ref>." }, { "from": "gpt", "value": "<ref>click on video option beside today option</ref><box>[[192, 846, 407, 934]]</box>" } ]
86
images/64468.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box for the element in the screen to complete the task: <ref>select to rememb on top of the page</ref>." }, { "from": "gpt", "value": "<ref>select to rememb on top of the page</ref><box>[[250, 32, 500, 95]]</box>" } ]
87
images/445.jpg
540
960
[ { "from": "human", "value": "<image>\nHighlight the area with bounding box that I can click to execute the task: <ref>go to the text next to the or buy ear spy pro</ref>." }, { "from": "gpt", "value": "<ref>go to the text next to the or buy ear spy pro</ref><box>[[757, 648, 975, 689]]</box>" }, { "from": "human", "value": "Task: <ref>click on the 299 button</ref>, output the bounding box of the area in the image that can complete the task." }, { "from": "gpt", "value": "<ref>click on the 299 button</ref><box>[[757, 198, 975, 240]]</box>" } ]
88
images/50959.jpg
540
960
[ { "from": "human", "value": "<image>\nOutput the bounding box of the element in the image that directly relates to solving this question: <ref>select the first image on the web page</ref>." }, { "from": "gpt", "value": "<ref>select the first image on the web page</ref><box>[[666, 434, 1000, 684]]</box>" } ]
89
images/22033.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nSpecify the bounding box coordinates for completing the instruction: <ref>click on the menu bar on the bottom right image</ref>." }, { "from": "gpt", "value": "<ref>click on the menu bar on the bottom right image</ref><box>[[932, 676, 990, 709]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>click on the heart symbol of the top right image</ref>." }, { "from": "gpt", "value": "<ref>click on the heart symbol of the top right image</ref><box>[[751, 344, 971, 378]]</box>" }, { "from": "human", "value": "Output the bounding box of the element in the image that directly relates to solving this question: <ref>select the number beside 20625</ref>." }, { "from": "gpt", "value": "<ref>select the number beside 20625</ref><box>[[751, 616, 971, 649]]</box>" }, { "from": "human", "value": "Identify the bounding box for the element in the screen to complete the task: <ref>select the third menu button above 8 like button</ref>." }, { "from": "gpt", "value": "<ref>select the third menu button above 8 like button</ref><box>[[426, 404, 485, 437]]</box>" } ]
90
images/68069.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease identify the area of the element with bounding box that can provide an answer to this question: <ref>click on the text which is just beside the arrow mark</ref>." }, { "from": "gpt", "value": "<ref>click on the text which is just beside the arrow mark</ref><box>[[136, 54, 1000, 88]]</box>" } ]
91
images/32770.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the region correctly responding to this task: <ref>select the first icon from the top right</ref>." }, { "from": "gpt", "value": "<ref>select the first icon from the top right</ref><box>[[902, 36, 975, 94]]</box>" }, { "from": "human", "value": "Highlight the click area with bounding box to complete the task: <ref>click on the download icon above exit</ref>." }, { "from": "gpt", "value": "<ref>click on the download icon above exit</ref><box>[[750, 635, 1000, 752]]</box>" }, { "from": "human", "value": "Please output the bounding box of the element correctly responding to this question: <ref>click on image which is above the text historybm</ref>." }, { "from": "gpt", "value": "<ref>click on image which is above the text historybm</ref><box>[[250, 655, 500, 709]]</box>" }, { "from": "human", "value": "Can you determine the bounding box coordinates to complete my task: <ref>select reload button</ref>." }, { "from": "gpt", "value": "<ref>select reload button</ref><box>[[780, 44, 853, 85]]</box>" }, { "from": "human", "value": "Where is the bounding box coordinates to click for solving the task: <ref>select the icon above add home</ref>." }, { "from": "gpt", "value": "<ref>select the icon above add home</ref><box>[[500, 655, 750, 709]]</box>" }, { "from": "human", "value": "What are the precise coordinates of the bounding box where I can click to finalize the instruction: <ref>click on the exit tab</ref>." }, { "from": "gpt", "value": "<ref>click on the exit tab</ref><box>[[750, 752, 1000, 868]]</box>" } ]
92
images/27903.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIdentify the bounding box coordinates that is relevant to the objective: <ref>select the symbol which is right to network</ref>." }, { "from": "gpt", "value": "<ref>select the symbol which is right to network</ref><box>[[562, 107, 980, 165]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>select network which is before redzone on the page</ref>." }, { "from": "gpt", "value": "<ref>select network which is before redzone on the page</ref><box>[[19, 107, 436, 165]]</box>" }, { "from": "human", "value": "Show me the bounding box coordinates that can provide an answer to the operation: <ref>click on the icon right to the american warrior networks</ref>." }, { "from": "gpt", "value": "<ref>click on the icon right to the american warrior networks</ref><box>[[935, 335, 962, 369]]</box>" }, { "from": "human", "value": "Identify the bounding box coordinates that is relevant to the objective: <ref>click on the right caret icon in which the text says antietam</ref>." }, { "from": "gpt", "value": "<ref>click on the right caret icon in which the text says antietam</ref><box>[[935, 397, 962, 431]]</box>" }, { "from": "human", "value": "Can you pinpoint the location with bounding box for completing the task: <ref>click on the button on right side to move foward or next</ref>." }, { "from": "gpt", "value": "<ref>click on the button on right side to move foward or next</ref><box>[[935, 583, 962, 618]]</box>" } ]
93
images/53551.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the precise location with bounding box that can solve the problem: <ref>select the start symbol</ref>." }, { "from": "gpt", "value": "<ref>select the start symbol</ref><box>[[591, 32, 727, 98]]</box>" }, { "from": "human", "value": "For the task: <ref>select the lock symbol which is on top left</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>select the lock symbol which is on top left</ref><box>[[863, 32, 1000, 98]]</box>" } ]
94
images/15106.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nPlease output the bounding box of the element correctly responding to this question: <ref>select the text below resend code</ref>." }, { "from": "gpt", "value": "<ref>select the text below resend code</ref><box>[[257, 562, 743, 617]]</box>" }, { "from": "human", "value": "For task: <ref>select the field which has number 9 beside 0</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>select the field which has number 9 beside 0</ref><box>[[524, 296, 664, 365]]</box>" }, { "from": "human", "value": "Specify the bounding box coordinates for completing the instruction: <ref>the cross mark symbol on the left of verify mobile</ref>." }, { "from": "gpt", "value": "<ref>the cross mark symbol on the left of verify mobile</ref><box>[[34, 172, 92, 205]]</box>" } ]
95
images/5267.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nWhat is the bounding box coordinates that is most relevant to this task: <ref>click the icon at the left side of groceries</ref>." }, { "from": "gpt", "value": "<ref>click the icon at the left side of groceries</ref><box>[[722, 122, 790, 161]]</box>" } ]
96
images/2445.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box to solve the task: <ref>click on calender icon at top left</ref>." }, { "from": "gpt", "value": "<ref>click on calender icon at top left</ref><box>[[38, 109, 79, 169]]</box>" }, { "from": "human", "value": "Point out the bounding box coordinates for completing the task: <ref>select the symbol which is left to the cuisine option</ref>." }, { "from": "gpt", "value": "<ref>select the symbol which is left to the cuisine option</ref><box>[[38, 661, 85, 738]]</box>" } ]
97
images/57600.jpg
540
960
[ { "from": "human", "value": "<image>\nIndicate the location with bounding box to solve the task: <ref>click on first image</ref>." }, { "from": "gpt", "value": "<ref>click on first image</ref><box>[[20, 109, 981, 366]]</box>" }, { "from": "human", "value": "For the task: <ref>click on the second frame</ref>, output the bounding box for the region in the image that is most relevant to answering the question." }, { "from": "gpt", "value": "<ref>click on the second frame</ref><box>[[20, 524, 981, 929]]</box>" } ]
98
images/38450.jpg
540
960
[ { "from": "human", "value": "<image>\nWhere is the bounding box coordinates to click for solving the task: <ref>click on the profile which is on the top left side</ref>." }, { "from": "gpt", "value": "<ref>click on the profile which is on the top left side</ref><box>[[29, 48, 107, 92]]</box>" } ]
99
images/76.jpg
1,080
1,920
[ { "from": "human", "value": "<image>\nFor task: <ref>select the icon on the top right of the web page beside clock icon</ref>, where should I click to complete the task, and provide the bounding box of the region." }, { "from": "gpt", "value": "<ref>select the icon on the top right of the web page beside clock icon</ref><box>[[883, 38, 1000, 104]]</box>" }, { "from": "human", "value": "Output the bounding box of the region to solve the task: <ref>click on the button which is next to the play</ref>." }, { "from": "gpt", "value": "<ref>click on the button which is next to the play</ref><box>[[550, 871, 635, 919]]</box>" }, { "from": "human", "value": "Please identify the area of the element with bounding box that can provide an answer to this question: <ref>click on the play button at the bottom of the page</ref>." }, { "from": "gpt", "value": "<ref>click on the play button at the bottom of the page</ref><box>[[364, 871, 449, 919]]</box>" } ]
End of preview.

No dataset card yet

Downloads last month
521