More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV
Paper • 2504.20032 • Published
Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
image_id: string
instance_id: string
label: string
caption: string
relations: list<item: list<item: string>>
child 0, item: list<item: string>
child 0, item: string
relation_subject: string
relation_parser: string
conversations: list<item: struct<from: string, value: string>>
child 0, item: struct<from: string, value: string>
child 0, from: string
child 1, value: string
image: string
to
{'conversations': List({'from': Value('string'), 'value': Value('string')}), 'image': Value('string')}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1835, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 621, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
image_id: string
instance_id: string
label: string
caption: string
relations: list<item: list<item: string>>
child 0, item: list<item: string>
child 0, item: string
relation_subject: string
relation_parser: string
conversations: list<item: struct<from: string, value: string>>
child 0, item: struct<from: string, value: string>
child 0, from: string
child 1, value: string
image: string
to
{'conversations': List({'from': Value('string'), 'value': Value('string')}), 'image': Value('string')}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1379, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 956, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
conversations list | image string |
|---|---|
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><567><402><272><232><angle><35></rbox><ref>expressway service area</ref><caption>A rectangular expressway service area li... | DIOR_R/images/train/13092.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><96><972><25><11><angle><27></rbox><ref>small car</ref><caption>A light-colored small car is parked near the curb in the lower-le... | FAIR1M/images/train/12275__800__0___200.png |
[
{
"from": "human",
"value": "Locate every object and write an individual caption describing its appearance, position, and nearby context."
},
{
"from": "assistant",
"value": "<rbox><602><586><479><76><angle><90></rbox><ref>chimney</ref><caption>A vertically oriented chimney with alternating redd... | DIOR_R/images/train/17675.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><418><420><16><7><angle><67></rbox><ref>vehicle</ref><caption>A small, bright, elongated vehicle is positione... | DIOR_R/images/train/19433.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><684><459><238><235><angle><90></rbox><ref>baseball field</ref><caption>A baseball field with a tan d... | DIOR_R/images/train/13198.jpg |
[
{
"from": "human",
"value": "Please detect all objects and describe each instance in relation to nearby objects, roads, buildings, water, or terrain."
},
{
"from": "assistant",
"value": "<rbox><394><911><25><13><angle><177></rbox><ref>tennis court</ref><caption>A blue tennis court located within... | DIOR_R/images/train/15859.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><66><200><12><5><angle><58></rbox><ref>vehicle</ref><caption>A small white vehicle is parked diagonal... | DIOR_R/images/train/20839.jpg |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><174><139><21><8><angle><147></rbox><ref>expressway toll station</ref><caption>A small, rectangular expr... | DIOR_R/images/train/15730.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><631><115><114><20><angle><76></rbox><ref>vehicle</ref><caption>A long white vehicle with a red cab travels diagonally al... | DIOR_R/images/train/05217.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><425><457><754><660><angle><90></rbox><ref>stadium</ref><caption>A large oval stadium features a central gree... | DIOR_R/images/train/04088.jpg |
[
{
"from": "human",
"value": "Locate all targets and write a separate caption for each, relating it to surrounding objects or land features when appropriate."
},
{
"from": "assistant",
"value": "<rbox><390><328><350><54><angle><135></rbox><ref>chimney</ref><caption>A long, narrow chimney oriented... | DIOR_R/images/train/15104.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><79><935><75><40><angle><126></rbox><ref>ground track field</ref><caption>A rectangular ground track ... | DIOR_R/images/train/23359.jpg |
[
{
"from": "human",
"value": "Find every object in the image and describe each one together with its surrounding objects or landscape features."
},
{
"from": "assistant",
"value": "<rbox><442><921><133><114><angle><179></rbox><ref>basketball court</ref><caption>A half-court basketball court marke... | DIOR_R/images/train/15919.jpg |
[
{
"from": "human",
"value": "Find all targets and caption each one with details about the instance and its spatial context."
},
{
"from": "assistant",
"value": "<rbox><366><470><853><594><angle><90></rbox><ref>stadium</ref><caption>An oval stadium features a red running track encircling a centra... | DIOR_R/images/train/01229.jpg |
[
{
"from": "human",
"value": "Detect every object in the aerial scene and describe its visual traits, position, and relevant neighboring features."
},
{
"from": "assistant",
"value": "<rbox><479><565><508><204><angle><90></rbox><ref>car</ref><caption>A dark-colored car is parked parallel to a bri... | CODrone/images/train/day_xidian_30m_90c_frame_4600__800__1800___0.png |
[
{
"from": "human",
"value": "Identify all objects in this aerial image and caption each instance with useful spatial relationships to its surroundings."
},
{
"from": "assistant",
"value": "<rbox><464><435><724><198><angle><4></rbox><ref>dam</ref><caption>The long, rectangular dam spans a wide, g... | DIOR_R/images/train/18648.jpg |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><513><445><675><108><angle><31></rbox><ref>ship</ref><caption>A long cargo ship with a pale deck and mul... | DIOR_R/images/train/04651.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and write a caption for each instance, describing the object itself and, when relevant, its spatial relationship to nearby objects or terrain."
},
{
"from": "assistant",
"value": "<rbox><414><464><381><99><angle><90></rbox><ref... | DIOR_R/images/train/14657.jpg |
[
{
"from": "human",
"value": "Locate and describe every object, mentioning nearby targets or geographic features when they help identify the instance."
},
{
"from": "assistant",
"value": "<rbox><535><821><244><244><angle><83></rbox><ref>baseball field</ref><caption>A baseball field with a curved ... | DIOR_R/images/train/01212.jpg |
[
{
"from": "human",
"value": "Locate every target in this remote-sensing image and caption its appearance and surrounding spatial context."
},
{
"from": "assistant",
"value": "<rbox><497><518><800><303><angle><144></rbox><ref>airport</ref><caption>The airport is a large, diagonally oriented compl... | DIOR_R/images/train/00858.jpg |
[
{
"from": "human",
"value": "Detect all objects in this remote-sensing image and caption each one using its appearance, location, and nearby scene context."
},
{
"from": "assistant",
"value": "<rbox><560><741><209><102><angle><70></rbox><ref>expressway toll station</ref><caption>The expressway t... | DIOR_R/images/train/21123.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and write a caption for each instance, describing the object itself and, when relevant, its spatial relationship to nearby objects or terrain."
},
{
"from": "assistant",
"value": "<rbox><271><609><146><66><angle><90></rbox><ref... | DIOR_R/images/train/18464.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><122><93><156><86><angle><0></rbox><ref>airplane</ref><caption>A large airplane is parked on the upper-left apron, with swept win... | DIOR_R/images/train/16566.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><713><171><45><19><angle><0></rbox><ref>ship</ref><caption>A small white ship is moored horizontally ... | DIOR_R/images/train/12982.jpg |
[
{
"from": "human",
"value": "Please detect all objects and describe each instance in relation to nearby objects, roads, buildings, water, or terrain."
},
{
"from": "assistant",
"value": "<rbox><321><643><206><149><angle><90></rbox><ref>football field</ref><caption>A green, vertically oriented fo... | FAIR1M/images/train/6254__800__1200___1200.png |
[
{
"from": "human",
"value": "Find all targets and caption each one with details about the instance and its spatial context."
},
{
"from": "assistant",
"value": "<rbox><236><617><301><141><angle><69></rbox><ref>tennis court</ref><caption>The leftmost blue tennis court, marked with white lines, si... | DIOR_R/images/train/00509.jpg |
[
{
"from": "human",
"value": "Find every object in the image and describe each one together with its surrounding objects or landscape features."
},
{
"from": "assistant",
"value": "<rbox><71><45><50><35><angle><0></rbox><ref>windmill</ref><caption>A white three-bladed windmill stands alone in the... | DIOR_R/images/train/17692.jpg |
[
{
"from": "human",
"value": "Find all object instances and write a concise caption for each, including relevant interactions with the surrounding scene."
},
{
"from": "assistant",
"value": "<rbox><532><447><681><326><angle><90></rbox><ref>golf course</ref><caption>A sprawling golf course with wi... | DIOR_R/images/train/05000.jpg |
[
{
"from": "human",
"value": "Please identify all objects and give each instance a concise description grounded in its local surroundings."
},
{
"from": "assistant",
"value": "<rbox><251><113><100><63><angle><90></rbox><ref>motorcycle</ref><caption>The motorcycle is a small, dark object positione... | CODrone/images/train/day_feitianyingbin_60m_90c_frame_3750__800__1200___1360.png |
[
{
"from": "human",
"value": "Locate every object and write an individual caption describing its appearance, position, and nearby context."
},
{
"from": "assistant",
"value": "<rbox><806><140><75><74><angle><81></rbox><ref>airplane</ref><caption>A yellow-fuselage airplane with gray wings is parke... | FAIR1M/images/train/10776__800__0___0.png |
[
{
"from": "human",
"value": "Identify all objects in this aerial image and caption each instance with useful spatial relationships to its surroundings."
},
{
"from": "assistant",
"value": "<rbox><602><398><305><224><angle><90></rbox><ref>chimney</ref><caption>The cylindrical chimney features a r... | DIOR_R/images/train/13869.jpg |
[
{
"from": "human",
"value": "Locate and describe every object, mentioning nearby targets or geographic features when they help identify the instance."
},
{
"from": "assistant",
"value": "<rbox><141><279><17><9><angle><94></rbox><ref>small car</ref><caption>A small car is parked near a house, pos... | FAIR1M/images/train/5576__800__200___0.png |
[
{
"from": "human",
"value": "Detect all objects in this remote-sensing image and caption each one using its appearance, location, and nearby scene context."
},
{
"from": "assistant",
"value": "<rbox><761><568><103><49><angle><1></rbox><ref>car</ref><caption>A red car faces left on the upper lane... | CODrone/images/train/day_tingzhouyuan_60m_30c_frame_900__800__3000___600.png |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><815><272><164><78><angle><90></rbox><ref>car</ref><caption>A white car is parked vertically along the r... | CODrone/images/train/night_yuemeihu_100m_90c_frame_2400__800__2400___1360.png |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><465><596><389><159><angle><41></rbox><ref>dam</ref><caption>A curved concrete dam spans a narrow channel between two dar... | DIOR_R/images/train/13911.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><496><523><379><120><angle><1></rbox><ref>train station</ref><caption>The elongated train station features multiple parallel plat... | DIOR_R/images/train/17952.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><202><436><131><36><angle><45></rbox><ref>windmill</ref><caption>The windmill on the left casts a long dark shadow across the bar... | DIOR_R/images/train/04659.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><488><301><311><303><angle><0></rbox><ref>chimney</ref><caption>A large circular chimney with a dark central ... | DIOR_R/images/train/03755.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><552><647><333><186><angle><51></rbox><ref>expressway service area</ref><caption>A wedge-shaped expressway service area l... | DIOR_R/images/train/15711.jpg |
[
{
"from": "human",
"value": "Please identify all objects and give each instance a concise description grounded in its local surroundings."
},
{
"from": "assistant",
"value": "<rbox><114><324><84><80><angle><90></rbox><ref>storage tank</ref><caption>A circular storage tank with a radial roof patt... | DIOR_R/images/train/21333.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><428><430><143><143><angle><0></rbox><ref>baseball field</ref><caption>A circular, light-gray baseball field ... | DIOR_R/images/train/23159.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><758><329><18><9><angle><125></rbox><ref>van</ref><caption>A white van travels along a paved road bordering a... | FAIR1M/images/train/3460__800__200___0.png |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><659><222><71><16><angle><132></rbox><ref>vehicle</ref><caption>A long white vehicle is oriented diagonally on... | DIOR_R/images/train/03727.jpg |
[
{
"from": "human",
"value": "Identify all objects in the scene and describe each one with useful appearance and neighborhood information."
},
{
"from": "assistant",
"value": "<rbox><253><805><12><5><angle><129></rbox><ref>bridge</ref><caption>A small, light-toned bridge spans a dark river channe... | DIOR_R/images/train/13571.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><767><764><90><54><angle><90></rbox><ref>traffic sign</ref><caption>A rectangular traffic sign with a triangular warning symbol i... | CODrone/images/train/night _yangfanpark_30m_30c_5_frame_0__800__1800___600.png |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><332><477><906><396><angle><86></rbox><ref>ground track field</ref><caption>A vertically oriented ground trac... | DIOR_R/images/train/00992.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><563><455><468><137><angle><104></rbox><ref>airport</ref><caption>A small rural airport consisting of a single long diagonal runw... | DIOR_R/images/train/17628.jpg |
[
{
"from": "human",
"value": "Identify all objects in the scene and describe each one with useful appearance and neighborhood information."
},
{
"from": "assistant",
"value": "<rbox><202><415><240><224><angle><90></rbox><ref>airplane</ref><caption>A large gray airplane with swept wings, four unde... | DIOR_R/images/train/04265.jpg |
[
{
"from": "human",
"value": "Find every object in the image and describe each one together with its surrounding objects or landscape features."
},
{
"from": "assistant",
"value": "<rbox><553><668><809><310><angle><0></rbox><ref>expressway service area</ref><caption>The lower expressway service a... | DIOR_R/images/train/04975.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><144><362><199><93><angle><90></rbox><ref>tennis court</ref><caption>The blue tennis court is the leftmost of three court... | DIOR_R/images/train/01356.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><763><245><206><108><angle><134></rbox><ref>ground track field</ref><caption>An oval ground track fie... | DIOR_R/images/train/18616.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and write a caption for each instance, describing the object itself and, when relevant, its spatial relationship to nearby objects or terrain."
},
{
"from": "assistant",
"value": "<rbox><596><203><76><73><angle><90></rbox><ref>... | DIOR_R/images/train/02786.jpg |
[
{
"from": "human",
"value": "Detect all objects in this remote-sensing image and caption each one using its appearance, location, and nearby scene context."
},
{
"from": "assistant",
"value": "<rbox><586><363><88><64><angle><0></rbox><ref>harbor</ref><caption>The harbor is a small wooden dock ex... | DIOR_R/images/train/12006.jpg |
[
{
"from": "human",
"value": "Please identify all objects and give each instance a concise description grounded in its local surroundings."
},
{
"from": "assistant",
"value": "<rbox><733><726><436><426><angle><90></rbox><ref>baseball field</ref><caption>A tan baseball field with a curved outfield... | DIOR_R/images/train/05322.jpg |
[
{
"from": "human",
"value": "Identify all objects in this aerial image and caption each instance with useful spatial relationships to its surroundings."
},
{
"from": "assistant",
"value": "<rbox><430><677><19><10><angle><105></rbox><ref>expressway toll station</ref><caption>A small, light-colore... | DIOR_R/images/train/18828.jpg |
[
{
"from": "human",
"value": "Please locate all objects in this image and provide a context-aware caption for each instance."
},
{
"from": "assistant",
"value": "<rbox><969><44><83><25><angle><90></rbox><ref>ship</ref><caption>A white ship with an elongated hull is docked vertically at the upper-... | DIOR_R/images/train/22848.jpg |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><396><503><897><169><angle><67></rbox><ref>airport</ref><caption>The airport consists of a long, diagonal runw... | DIOR_R/images/train/03709.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><484><521><621><115><angle><145></rbox><ref>ship</ref><caption>A long reddish-decked ship with visible piping... | DIOR_R/images/train/22763.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><734><491><15><13><angle><15></rbox><ref>airplane</ref><caption>A small airplane is parked on the apron, oriented diagona... | DIOR_R/images/train/22092.jpg |
[
{
"from": "human",
"value": "Locate and describe every object, mentioning nearby targets or geographic features when they help identify the instance."
},
{
"from": "assistant",
"value": "<rbox><166><371><116><65><angle><90></rbox><ref>car</ref><caption>A light-colored car sits along the left edg... | CODrone/images/train/day_zhengchenggong_60m_30c_6_frame_6900__800__1800___1200.png |
[
{
"from": "human",
"value": "Find and caption every object, noting its location and meaningful relationships with nearby targets or terrain."
},
{
"from": "assistant",
"value": "<rbox><538><532><473><344><angle><0></rbox><ref>dam</ref><caption>A linear dam structure crosses a narrow waterway, fe... | DIOR_R/images/train/22365.jpg |
[
{
"from": "human",
"value": "Identify all objects in the scene and describe each one with useful appearance and neighborhood information."
},
{
"from": "assistant",
"value": "<rbox><374><471><287><287><angle><43></rbox><ref>baseball field</ref><caption>A diamond-shaped baseball field with tan di... | DIOR_R/images/train/02483.jpg |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><173><278><176><59><angle><90></rbox><ref>ship</ref><caption>A white ship is docked vertically at a mari... | DIOR_R/images/train/23416.jpg |
[
{
"from": "human",
"value": "Identify all objects in this aerial image and caption each instance with useful spatial relationships to its surroundings."
},
{
"from": "assistant",
"value": "<rbox><667><973><36><8><angle><20></rbox><ref>dry cargo ship</ref><caption>A small, elongated dry cargo shi... | FAIR1M/images/train/3539__800__0___200.png |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><227><573><33><12><angle><60></rbox><ref>vehicle</ref><caption>A vehicle is parked within a marked space in a ... | DIOR_R/images/train/04528.jpg |
[
{
"from": "human",
"value": "Please detect all objects and describe each instance in relation to nearby objects, roads, buildings, water, or terrain."
},
{
"from": "assistant",
"value": "<rbox><846><924><44><16><angle><178></rbox><ref>dump truck</ref><caption>A small dump truck with a light cab ... | FAIR1M/images/train/2928__800__200___0.png |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><643><471><797><179><angle><72></rbox><ref>airport</ref><caption>The airport is a long, narrow comple... | DIOR_R/images/train/15763.jpg |
[
{
"from": "human",
"value": "Identify all objects in the scene and describe each one with useful appearance and neighborhood information."
},
{
"from": "assistant",
"value": "<rbox><771><853><83><31><angle><5></rbox><ref>vehicle</ref><caption>A light-colored vehicle is parked horizontally in a c... | DIOR_R/images/train/05435.jpg |
[
{
"from": "human",
"value": "Detect all object instances and describe where each one appears relative to nearby objects or geographic features."
},
{
"from": "assistant",
"value": "<rbox><494><856><32><13><angle><79></rbox><ref>vehicle</ref><caption>A white vehicle travels along a multi-lane hig... | DIOR_R/images/train/16823.jpg |
[
{
"from": "human",
"value": "Find all targets and caption each one with details about the instance and its spatial context."
},
{
"from": "assistant",
"value": "<rbox><838><339><10><5><angle><97></rbox><ref>bridge</ref><caption>A small bridge on the right side of the image spans a green linear w... | DIOR_R/images/train/11912.jpg |
[
{
"from": "human",
"value": "Please identify all objects and give each instance a concise description grounded in its local surroundings."
},
{
"from": "assistant",
"value": "<rbox><859><869><66><58><angle><90></rbox><ref>stadium</ref><caption>A ring-shaped stadium with a reddish-brown outer str... | DIOR_R/images/train/16302.jpg |
[
{
"from": "human",
"value": "Please detect all objects and describe each instance in relation to nearby objects, roads, buildings, water, or terrain."
},
{
"from": "assistant",
"value": "<rbox><367><945><95><79><angle><90></rbox><ref>motorcycle</ref><caption>A motorcycle with a rider in a yellow... | CODrone/images/train/day_hudongpark_60m_30c_4_frame_5400__800__1800___1360.png |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><148><275><112><101><angle><93></rbox><ref>tennis court</ref><caption>A blue-surfaced tennis court with white ... | DIOR_R/images/train/01990.jpg |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><797><657><36><26><angle><90></rbox><ref>storage tank</ref><caption>A circular, pale-topped storage tank... | DIOR_R/images/train/22228.jpg |
[
{
"from": "human",
"value": "Locate every object and write an individual caption describing its appearance, position, and nearby context."
},
{
"from": "assistant",
"value": "<rbox><273><277><75><54><angle><0></rbox><ref>windmill</ref><caption>A white-bladed windmill in the upper-left casts a lo... | DIOR_R/images/train/19178.jpg |
[
{
"from": "human",
"value": "Locate and describe every object, mentioning nearby targets or geographic features when they help identify the instance."
},
{
"from": "assistant",
"value": "<rbox><145><111><28><12><angle><18></rbox><ref>van</ref><caption>A van is parked in a designated space within... | FAIR1M/images/train/9637__800__0___0.png |
[
{
"from": "human",
"value": "Please detect every instance and write a short caption connecting it to its immediate visual environment when relevant."
},
{
"from": "assistant",
"value": "<rbox><163><386><49><14><angle><0></rbox><ref>windmill</ref><caption>A windmill stands on the left hillside, i... | DIOR_R/images/train/18601.jpg |
[
{
"from": "human",
"value": "Please locate every target and provide an instance-level caption with relevant visual and spatial context."
},
{
"from": "assistant",
"value": "<rbox><215><65><86><82><angle><135></rbox><ref>airplane</ref><caption>A white airplane is parked diagonally at the upper-le... | DIOR_R/images/train/19976.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><88><319><164><144><angle><0></rbox><ref>storage tank</ref><caption>A large circular storage tank with a radial roof patt... | DIOR_R/images/train/13128.jpg |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><42><48><26><12><angle><72></rbox><ref>small car</ref><caption>A white small car is parked diagonally in a mar... | FAIR1M/images/train/1319__800__0___0.png |
[
{
"from": "human",
"value": "Identify all objects in this aerial image and caption each instance with useful spatial relationships to its surroundings."
},
{
"from": "assistant",
"value": "<rbox><510><435><880><363><angle><0></rbox><ref>golf course</ref><caption>A large golf course with winding ... | DIOR_R/images/train/04968.jpg |
[
{
"from": "human",
"value": "Please locate each visible target and provide a concise instance description with relevant environmental context."
},
{
"from": "assistant",
"value": "<rbox><536><435><730><146><angle><60></rbox><ref>airport</ref><caption>A small airport featuring a single dark runwa... | DIOR_R/images/train/11791.jpg |
[
{
"from": "human",
"value": "Locate each object in the image and describe it alongside any useful nearby objects or scene elements."
},
{
"from": "assistant",
"value": "<rbox><604><762><192><89><angle><131></rbox><ref>tennis court</ref><caption>A dark-surfaced tennis court with white boundary li... | DIOR_R/images/train/21570.jpg |
[
{
"from": "human",
"value": "Identify and describe all objects, including helpful relationships to nearby structures, vehicles, vegetation, or terrain."
},
{
"from": "assistant",
"value": "<rbox><304><663><156><73><angle><89></rbox><ref>tennis court</ref><caption>A rectangular, vertically orient... | DIOR_R/images/train/13792.jpg |
End of preview.
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
RICapBench
RICapBench is a dataset and benchmark built based on images from DIOR-R, CODrone, and FAIR1M v2.0. For usage instructions and evaluation code, see the RICapBench GitHub repository.
Files and splits
train.jsonlval.jsonlevaluation.jsonl: benchmark annotations.evaluation-spatial-gt-relations.jsonl: spatial-relation ground truth for evaluation.images.7z: source images.
| Source dataset | RICapBench train |
RICapBench val and evaluation |
|---|---|---|
| DIOR-R | Original train and test splits |
Original val split |
| CODrone | Original train split |
Original val split |
| FAIR1M v2.0 | Original train split |
Original val split |
RICapBench val and evaluation are non-overlapping subsets of the source validation splits; these images are excluded from RICapBench train. The table identifies source pools, not inclusion of every source image.
Licensing and attribution
Unless otherwise noted, files in this repository are licensed under CC BY 4.0. Third-party images and inherited annotations retain their source licenses.
| Source | License / terms |
|---|---|
| DIOR-R | CC BY-NC 4.0 |
| CODrone | CC BY-NC-SA 4.0 |
| FAIR1M v2.0 | CC BY-NC-SA 3.0; academic use only |
Acknowledgements and citations
We thank the DIOR/DIOR-R, CODrone, and FAIR1M authors. Please credit RICapBench and cite the relevant source papers, including both DIOR and DIOR-R for that component. The FAIR1M paper below accompanies the source dataset; this benchmark uses its v2.0 release.
- DIOR: Ke Li, Gang Wan, Gong Cheng, Liqiu Meng, and Junwei Han. “Object detection in optical remote sensing images: A survey and a new benchmark.” ISPRS Journal of Photogrammetry and Remote Sensing, 159, 296–307, 2020. Paper.
- DIOR-R: Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, and Junwei Han. “Anchor-Free Oriented Proposal Generator for Object Detection.” IEEE Transactions on Geoscience and Remote Sensing, 2022. Author preprint.
- CODrone: Kai Ye, Haidi Tang, Bowen Liu, Pingyang Dai, Liujuan Cao, and Rongrong Ji. “More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV.” arXiv preprint arXiv:2504.20032, 2025. Paper.
- FAIR1M: Xian Sun et al. “FAIR1M: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery.” ISPRS Journal of Photogrammetry and Remote Sensing, 184, 116–130, 2022. Paper and full author list.
- Downloads last month
- -