{"url":"/dataset/first-person-hand-action-benchmark","name":"First-Person Hand Action Benchmark","full_name":null,"description_markdown":"**First-Person Hand Action Benchmark** is a collection of RGB-D video sequences comprised of more than 100K frames of 45 daily hand action categories, involving 26 different objects in several hand configurations. \r\n\r\nSource: [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://arxiv.org/pdf/1704.02463v2.pdf)","description_withheld":null,"homepage":"https://kcvl-kaist.github.io/FPHA/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/first-person-hand-action-benchmark-with-rgb-d","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","first_author":"Guillermo Garcia-Hernando","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://github.com/guiggh/hand_pose_action?tab=readme-ov-file#terms-and-conditions"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Pose Estimation","url":"/task/pose-estimation","datasets_with_task":"/datasets/task/pose-estimation"},{"name":"Activity Recognition","url":"/task/activity-recognition","datasets_with_task":"/datasets/task/activity-recognition"},{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"},{"name":"Hand Pose Estimation","url":"/task/hand-pose-estimation","datasets_with_task":"/datasets/task/hand-pose-estimation"},{"name":"3D Hand Pose Estimation","url":"/task/3d-hand-pose-estimation","datasets_with_task":"/datasets/task/3d-hand-pose-estimation"}],"languages":[],"variants":["First-Person Hand Action Benchmark"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-first","task":"Skeleton Based Action Recognition","dataset_variant":"First-Person Hand Action Benchmark","rows":4,"metrics":["1:3 Accuracy","1:1 Accuracy","3:1 Accuracy","Cross-person Accuracy"],"first_row_in_archive_order":{"model":"TCN-Summ","paper":"/paper/domain-and-view-point-agnostic-hand-action","metrics":{"1:1 Accuracy":"95.93","1:3 Accuracy":"92.9","3:1 Accuracy":"96.76","Cross-person Accuracy":"88.70"},"code_links":[{"title":"AlbertoSabater/Domain-and-View-point-Agnostic-Hand-Action-Recognition","url":"https://github.com/AlbertoSabater/Domain-and-View-point-Agnostic-Hand-Action-Recognition"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/activity-recognition-on-first-person-hand","task":"Activity Recognition","dataset_variant":"First-Person Hand Action Benchmark","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Boutaleb et al.","paper":"/paper/multi-stage-rgb-based-transfer-learning","metrics":{"1:1 Accuracy":"97.91"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/real-time-hand-gesture-recognition","title":"Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN","date":"2024-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/in-my-perspective-in-my-hands-accurate","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","date":"2024-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-stage-rgb-based-transfer-learning","title":"Multi-stage RGB-based Transfer Learning Pipeline for Hand Activity Recognition","date":"2022-02-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/domain-and-view-point-agnostic-hand-action","title":"Domain and View-point Agnostic Hand Action Recognition","date":"2021-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-multi-stream-temporal-learning-and","title":"Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition","date":"2021-02-10","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}