The dataset viewer is not available for this dataset.
Error code: ConfigNamesError
Exception: FileNotFoundError
Message: Couldn't find any data file at /src/services/worker/SadeghRahmaniB/BiScopeCap. Couldn't find 'SadeghRahmaniB/BiScopeCap' on the Hugging Face Hub either: FileNotFoundError: Unable to find 'hf://datasets/SadeghRahmaniB/BiScopeCap@878359c730825c35322cee3d88c3e91f2307e66a/biscopecap_train.json' with any supported extension ['.csv', '.tsv', '.json', '.jsonl', '.ndjson', '.parquet', '.geoparquet', '.gpq', '.arrow', '.txt', '.conll', '.conllu', '.tar', '.xml', '.hdf5', '.h5', '.eval', '.toml', '.md', '.lance', '.tsfile', '.vortex', '.fa', '.fasta', '.fna', '.ffn', '.faa', '.frn', '.afa', '.gb', '.gbk', '.genbank', '.fq', '.fastq', '.pdb', '.ent', '.cif', '.mmcif', '.PDB', '.ENT', '.blp', '.bmp', '.dib', '.bufr', '.cur', '.pcx', '.dcx', '.dds', '.ps', '.eps', '.fit', '.fits', '.fli', '.flc', '.ftc', '.ftu', '.gbr', '.gif', '.grib', '.png', '.apng', '.jp2', '.j2k', '.jpc', '.jpf', '.jpx', '.j2c', '.icns', '.ico', '.im', '.iim', '.tif', '.tiff', '.jfif', '.jpe', '.jpg', '.jpeg', '.mpg', '.mpeg', '.msp', '.pcd', '.pxr', '.pbm', '.pgm', '.ppm', '.pnm', '.psd', '.bw', '.rgb', '.rgba', '.sgi', '.ras', '.tga', '.icb', '.vda', '.vst', '.webp', '.wmf', '.emf', '.xbm', '.xpm', '.BLP', '.BMP', '.DIB', '.BUFR', '.CUR', '.PCX', '.DCX', '.DDS', '.PS', '.EPS', '.FIT', '.FITS', '.FLI', '.FLC', '.FTC', '.FTU', '.GBR', '.GIF', '.GRIB', '.PNG', '.APNG', '.JP2', '.J2K', '.JPC', '.JPF', '.JPX', '.J2C', '.ICNS', '.ICO', '.IM', '.IIM', '.TIF', '.TIFF', '.JFIF', '.JPE', '.JPG', '.JPEG', '.MPG', '.MPEG', '.MSP', '.PCD', '.PXR', '.PBM', '.PGM', '.PPM', '.PNM', '.PSD', '.BW', '.RGB', '.RGBA', '.SGI', '.RAS', '.TGA', '.ICB', '.VDA', '.VST', '.WEBP', '.WMF', '.EMF', '.XBM', '.XPM', '.aiff', '.au', '.avr', '.caf', '.flac', '.htk', '.svx', '.mat4', '.mat5', '.mpc2k', '.ogg', '.paf', '.pvf', '.raw', '.rf64', '.sd2', '.sds', '.ircam', '.voc', '.w64', '.wav', '.nist', '.wavex', '.wve', '.xi', '.mp3', '.opus', '.3gp', '.3g2', '.avi', '.asf', '.flv', '.mp4', '.mov', '.m4v', '.mkv', '.webm', '.f4v', '.wmv', '.wma', '.ogm', '.mxf', '.nut', '.AIFF', '.AU', '.AVR', '.CAF', '.FLAC', '.HTK', '.SVX', '.MAT4', '.MAT5', '.MPC2K', '.OGG', '.PAF', '.PVF', '.RAW', '.RF64', '.SD2', '.SDS', '.IRCAM', '.VOC', '.W64', '.WAV', '.NIST', '.WAVEX', '.WVE', '.XI', '.MP3', '.OPUS', '.3GP', '.3G2', '.AVI', '.ASF', '.FLV', '.MP4', '.MOV', '.M4V', '.MKV', '.WEBM', '.F4V', '.WMV', '.WMA', '.OGM', '.MXF', '.NUT', '.glb', '.ply', '.stl', '.GLB', '.PLY', '.STL', '.pdf', '.PDF', '.nii', '.NII', '.zip', '.idx', '.manifest', '.txn']
Traceback: Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/dataset/config_names.py", line 67, in compute_config_names_response
config_names = get_dataset_config_names(
path=dataset,
token=hf_token,
)
File "/usr/local/lib/python3.14/site-packages/datasets/inspect.py", line 161, in get_dataset_config_names
dataset_module = dataset_module_factory(
path,
...<4 lines>...
**download_kwargs,
)
File "/usr/local/lib/python3.14/site-packages/datasets/load.py", line 1178, in dataset_module_factory
raise FileNotFoundError(
...<2 lines>...
) from None
FileNotFoundError: Couldn't find any data file at /src/services/worker/SadeghRahmaniB/BiScopeCap. Couldn't find 'SadeghRahmaniB/BiScopeCap' on the Hugging Face Hub either: FileNotFoundError: Unable to find 'hf://datasets/SadeghRahmaniB/BiScopeCap@878359c730825c35322cee3d88c3e91f2307e66a/biscopecap_train.json' with any supported extension ['.csv', '.tsv', '.json', '.jsonl', '.ndjson', '.parquet', '.geoparquet', '.gpq', '.arrow', '.txt', '.conll', '.conllu', '.tar', '.xml', '.hdf5', '.h5', '.eval', '.toml', '.md', '.lance', '.tsfile', '.vortex', '.fa', '.fasta', '.fna', '.ffn', '.faa', '.frn', '.afa', '.gb', '.gbk', '.genbank', '.fq', '.fastq', '.pdb', '.ent', '.cif', '.mmcif', '.PDB', '.ENT', '.blp', '.bmp', '.dib', '.bufr', '.cur', '.pcx', '.dcx', '.dds', '.ps', '.eps', '.fit', '.fits', '.fli', '.flc', '.ftc', '.ftu', '.gbr', '.gif', '.grib', '.png', '.apng', '.jp2', '.j2k', '.jpc', '.jpf', '.jpx', '.j2c', '.icns', '.ico', '.im', '.iim', '.tif', '.tiff', '.jfif', '.jpe', '.jpg', '.jpeg', '.mpg', '.mpeg', '.msp', '.pcd', '.pxr', '.pbm', '.pgm', '.ppm', '.pnm', '.psd', '.bw', '.rgb', '.rgba', '.sgi', '.ras', '.tga', '.icb', '.vda', '.vst', '.webp', '.wmf', '.emf', '.xbm', '.xpm', '.BLP', '.BMP', '.DIB', '.BUFR', '.CUR', '.PCX', '.DCX', '.DDS', '.PS', '.EPS', '.FIT', '.FITS', '.FLI', '.FLC', '.FTC', '.FTU', '.GBR', '.GIF', '.GRIB', '.PNG', '.APNG', '.JP2', '.J2K', '.JPC', '.JPF', '.JPX', '.J2C', '.ICNS', '.ICO', '.IM', '.IIM', '.TIF', '.TIFF', '.JFIF', '.JPE', '.JPG', '.JPEG', '.MPG', '.MPEG', '.MSP', '.PCD', '.PXR', '.PBM', '.PGM', '.PPM', '.PNM', '.PSD', '.BW', '.RGB', '.RGBA', '.SGI', '.RAS', '.TGA', '.ICB', '.VDA', '.VST', '.WEBP', '.WMF', '.EMF', '.XBM', '.XPM', '.aiff', '.au', '.avr', '.caf', '.flac', '.htk', '.svx', '.mat4', '.mat5', '.mpc2k', '.ogg', '.paf', '.pvf', '.raw', '.rf64', '.sd2', '.sds', '.ircam', '.voc', '.w64', '.wav', '.nist', '.wavex', '.wve', '.xi', '.mp3', '.opus', '.3gp', '.3g2', '.avi', '.asf', '.flv', '.mp4', '.mov', '.m4v', '.mkv', '.webm', '.f4v', '.wmv', '.wma', '.ogm', '.mxf', '.nut', '.AIFF', '.AU', '.AVR', '.CAF', '.FLAC', '.HTK', '.SVX', '.MAT4', '.MAT5', '.MPC2K', '.OGG', '.PAF', '.PVF', '.RAW', '.RF64', '.SD2', '.SDS', '.IRCAM', '.VOC', '.W64', '.WAV', '.NIST', '.WAVEX', '.WVE', '.XI', '.MP3', '.OPUS', '.3GP', '.3G2', '.AVI', '.ASF', '.FLV', '.MP4', '.MOV', '.M4V', '.MKV', '.WEBM', '.F4V', '.WMV', '.WMA', '.OGM', '.MXF', '.NUT', '.glb', '.ply', '.stl', '.GLB', '.PLY', '.STL', '.pdf', '.PDF', '.nii', '.NII', '.zip', '.idx', '.manifest', '.txn']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.
BiScopeCap-100K
BiScopeCap is a video-level egocentric captioning dataset for sub-action detection: recognising the high-level action in a clip and the separate roles of the left and right hands, together with the objects each hand manipulates. Each caption is paired with structured spatial metadata (per-keyframe bounding boxes for hands and objects).
It was introduced in:
Sub-actions in Action: Text-Guided Hand-Role Alignment for Sub-Action Recognition Sadegh Rahmaniboldaji, Filip Rybansky, Quoc Vuong, Frank Guerin, Andrew Gilbert BMVC 2026 Paper · Project page · Code
Dataset summary
Most egocentric benchmarks describe only the high-level action ("a person is picking up a pan"). BiScopeCap also captures what each hand does within that action:
A person is washing a plate. The left hand holds the plate, while the right hand uses a sponge to clean it.
Captions were built by standardising and enriching annotations from EPIC-KITCHENS / EPIC-VISOR, Ego4D, HD-EPIC and HOI-QA. They were consolidated into video-level captions with Gemini 2.0 Flash, conditioned on human narrations and annotated hand/object regions. Each caption follows a unified format:
- the high-level action,
- the left- and right-hand roles (when the hand is visible or active),
- spatial metadata in a
<meta>…</meta>span.
No videos are distributed in this repository. Only annotations are released. Clips have to be obtained from the original datasets and cut using the identifiers below (see Obtaining the videos).
Dataset structure
Splits
| Source subset | Train | Test |
|---|---|---|
| EPIC-KITCHENS / VISOR | 31,432 | 3,729 |
| Ego4D | 22,916 | 3,304 |
| HD-EPIC | 38,520 | 2,846 |
| Total | 92,868 | 9,879 |
Data fields
Each record follows the LLaVA / VideoChatGPT conversation format:
{
"id": "P01_107_0",
"video": "P01_107_0",
"key_frames": [21, 58],
"conversations": [
{"from": "human", "value": "describe the action in the video. \n<video>"},
{"from": "gpt", "value": "A person is closing a door. The right hand is holding and manipulating the door to close it. <meta>[{\"frame\": 21, \"object\": \"door\", \"bbox\": [118, 0, 106, 199]}, {\"frame\": 21, \"object\": \"right hand\", \"bbox\": [155, 151, 21, 73]}, ...]</meta>"}
]
}
| Field | Type | Description |
|---|---|---|
id |
string | Unique clip identifier. Its format shows the source subset (see below). |
video |
string | Clip file name (without extension) that the record refers to. |
key_frames |
list[int] | Frame indices in the clip that the spatial metadata refers to. |
conversations |
list[dict] | One human prompt plus one gpt target caption. |
Caption and metadata. The target caption is natural language followed by a <meta>…</meta> span holding a JSON list of entries:
| Key | Description |
|---|---|
frame |
Keyframe index (one of key_frames). |
object |
Object label, including "left hand" / "right hand". |
bbox |
[x, y, w, h] in pixels, in the 224 × 224 resized frame. |
To get the plain caption, strip everything from <meta> onwards. Every record has a well-formed <meta> span.
ID formats by source
| Source | Example id |
|---|---|
| EPIC-KITCHENS / VISOR | P01_107_0 (<video_id>_<narration_index>) |
| HD-EPIC | P01-20240202-110250-1 |
| Ego4D | <video_uid>_<clip_uid>_<annotation_uid> |
Loading
from datasets import load_dataset
import json, re
ds = load_dataset("TODO-org/BiScopeCap") # TODO: repo id
def split_caption(text):
m = re.search(r"<meta>(.*)</meta>", text, re.S)
caption = text[: m.start()].strip() if m else text.strip()
meta = json.loads(m.group(1)) if m else []
return caption, meta
caption, meta = split_caption(ds["train"][0]["conversations"][1]["value"])
Obtaining the videos
BiScopeCap does not redistribute any video. To use it:
- Download the source videos under their own licences:
- EPIC-KITCHENS-100 / VISOR: https://epic-kitchens.github.io
- Ego4D: https://ego4d-data.org (licence agreement required)
- HD-EPIC: https://hd-epic.github.io
- Trim clips at the narration timestamps and resize them to the model input resolution (224 × 224 in our experiments).
- Name each clip after its
videofield.
Dataset creation
Curation pipeline
- Per-source processing. EPIC-KITCHENS and Ego4D supply narrations and temporal boundaries. EPIC-VISOR segmentations, processed by HOI-QA, supply hand/object boxes and keyframe captions. HD-EPIC supplies video-level hand-motion descriptions, reformulated to add the missing high-level action and structured metadata.
- Caption generation. Gemini 2.0 Flash (May–Sep 2025) summarises these signals into one video-level caption per clip. It is conditioned on the human narration and the annotated regions, so the hand-role attribution stays grounded.
- Video cropper and caption adjuster. Clips are segmented by narration timestamps and resized. Bounding boxes are re-aligned spatially and temporally to the resized keyframes.
Statistics
- 12,814 action instances and 5,727 active objects, including hands.
- Most frequent objects other than hands: pan (4,294), tap (4,271), knife (4,271), sink (3,180), plate (3,073).
- Left-hand, right-hand and bimanual interactions are all well represented. A small number of captions mention no hand.
Annotation quality
A manual audit of 200 randomly sampled training clips, balanced across sources, found:
- ≈5% with minor descriptive inaccuracies (e.g. imprecise verbs),
- ≈8% with left-hand hallucination,
- ≈10% with right-hand hallucination.
Captions are machine-generated and should be treated as noisy supervision. They are not exhaustive ground truth.
Uses
Intended uses
- Training and evaluating video-language models for fine-grained, hand-aware egocentric captioning.
- Sub-action detection: identifying the left- and right-hand roles within a high-level action.
- Research on grounded captioning that uses the spatial
<meta>annotations.
Out-of-scope uses
- Commercial use, subject to the upstream licences.
- Identifying or profiling individuals in the source recordings.
- Using the captions as verified ground truth in safety-critical settings. They are machine-generated and contain noise.
Licence
The annotations in this repository are released under TODO (e.g. CC BY-NC 4.0). Using them also requires following the licences of the source datasets: EPIC-KITCHENS / VISOR, Ego4D and HD-EPIC. No raw video is redistributed.
Citation
@inproceedings{rahmaniboldaji2026subactions,
title = {Sub-actions in Action: Text-Guided Hand-Role Alignment for Sub-Action Recognition},
author = {Rahmaniboldaji, Sadegh and Rybansky, Filip and Vuong, Quoc and Guerin, Frank and Gilbert, Andrew},
booktitle = {British Machine Vision Conference (BMVC)},
year = {2026}
}
Please also cite the source datasets: EPIC-KITCHENS-100, EPIC-KITCHENS VISOR, Ego4D, HD-EPIC and HOI-Ref.
Acknowledgements
This work was funded by the Leverhulme Trust Research Project Grant RPG-2023-079.
- Downloads last month
- 106