{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/first-person-hand-action-benchmark-with-rgb-d","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","arxiv_id":"1704.02463","date":"2017-04-08","proceeding":"CVPR 2018 6","authors":["Guillermo Garcia-Hernando","Shanxin Yuan","Seungryul Baek","Tae-Kyun Kim"],"abstract":"In this work we study the use of 3D hand poses to recognize first-person\ndynamic hand actions interacting with 3D objects. Towards this goal, we\ncollected RGB-D video sequences comprised of more than 100K frames of 45 daily\nhand action categories, involving 26 different objects in several hand\nconfigurations. To obtain hand pose annotations, we used our own mo-cap system\nthat automatically infers the 3D location of each of the 21 joints of a hand\nmodel via 6 magnetic sensors and inverse kinematics. Additionally, we recorded\nthe 6D object poses and provide 3D object models for a subset of hand-object\ninteraction sequences. To the best of our knowledge, this is the first\nbenchmark that enables the study of first-person hand actions with the use of\n3D hand poses. We present an extensive experimental evaluation of RGB-D and\npose-based action recognition by 18 baselines/state-of-the-art approaches. The\nimpact of using appearance features, poses, and their combinations are\nmeasured, and the different training/testing protocols are evaluated. Finally,\nwe assess how ready the 3D hand pose estimation field is when hands are\nseverely occluded by objects in egocentric views and its influence on action\nrecognition. From the results, we see clear benefits of using hand pose as a\ncue for action recognition compared to other data modalities. Our dataset and\nexperiments can be of interest to communities of 3D hand pose estimation, 6D\nobject pose, and robotics as well as action recognition.","url_abs":"http://arxiv.org/abs/1704.02463v2","url_pdf":"http://arxiv.org/pdf/1704.02463v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"first-person-hand-action-benchmark-with-rgb-d","repo_url":"https://github.com/guiggh/hand_pose_action","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"egocentric-activity-recognition","task_name":"Egocentric Activity Recognition"},{"task_slug":"hand-gesture-recognition","task_name":"Hand Gesture Recognition"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[{"slug":"first-person-hand-action-benchmark","name":"First-Person Hand Action Benchmark","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.02463","atlas_url":"https://app.syntology.ai/?focus=1704.02463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.02463"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guiggh/hand_pose_action","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"31879f55ffdd2b9a","entry":"get_obj_transform","repo":"guiggh/hand_pose_action","repo_kind":"listed","path":"load_example.py","file_url":"https://github.com/guiggh/hand_pose_action/blob/HEAD/load_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31879f55ffdd2b9a"}},{"code_sha256_prefix":"41da703c60f382e8","entry":"get_skeleton","repo":"guiggh/hand_pose_action","repo_kind":"listed","path":"load_example.py","file_url":"https://github.com/guiggh/hand_pose_action/blob/HEAD/load_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41da703c60f382e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}