{"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/hierarchical-temporal-transformer-for-3d-hand","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","arxiv_id":"2209.09484","date":"2022-09-20","proceeding":"CVPR 2023 1","authors":["Yilin Wen","Hao Pan","Lei Yang","Jia Pan","Taku Komura","Wenping Wang"],"abstract":"Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame pose and object information over a longer time span to recognize the action. Our approach achieves competitive results on two first-person hand action benchmarks, namely FPHA and H2O. Extensive ablation studies verify our design choices.","url_abs":"https://arxiv.org/abs/2209.09484v4","url_pdf":"https://arxiv.org/pdf/2209.09484v4.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":"hierarchical-temporal-transformer-for-3d-hand","repo_url":"https://github.com/fylwen/htt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-on-h2o-2-hands-and-objects","task":"Action Recognition","dataset":"H2O  (2 Hands and Objects)","model":"HTT","rank_in_archive_order":6,"of":11,"metrics":{"Actions Top-1":"86.36","Hand Pose":"3D (est.)","Object Label":"Yes (est.)","Object Pose":"No","RGB":"Yes"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.09484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09484"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/fylwen/htt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"fylwen/htt","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"6ba5634d0eca83b8","entry":"compute_hand_loss","repo":"fylwen/htt","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba5634d0eca83b8"}},{"code_sha256_prefix":"d84e7bf13e0f97c7","entry":"load_opts","repo":"fylwen/htt","repo_kind":"official","path":"netscripts/reloadmodel.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/netscripts/reloadmodel.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d84e7bf13e0f97c7"}},{"code_sha256_prefix":"d921e2ab2e6c7662","entry":"parse_evaluators","repo":"fylwen/htt","repo_kind":"official","path":"netscripts/position_evaluator.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/netscripts/position_evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d921e2ab2e6c7662"}},{"code_sha256_prefix":"327766cdbd033189","entry":"recover_3d_proj_pinhole","repo":"fylwen/htt","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"327766cdbd033189"}},{"code_sha256_prefix":"75131af8f1e8c065","entry":"resnet18","repo":"fylwen/htt","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75131af8f1e8c065"}},{"code_sha256_prefix":"abce9f8e2e1ff31d","entry":"resnet34","repo":"fylwen/htt","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abce9f8e2e1ff31d"}},{"code_sha256_prefix":"c543ebbcba3e5933","entry":"torch2numpy","repo":"fylwen/htt","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/fylwen/htt/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c543ebbcba3e5933"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}