{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/pose-and-joint-aware-action-recognition","title":"Pose And Joint-Aware Action Recognition","arxiv_id":"2010.08164","date":"2020-10-16","proceeding":null,"authors":["Anshul Shah","Shlok Mishra","Ankan Bansal","Jun-Cheng Chen","Rama Chellappa","Abhinav Shrivastava"],"abstract":"Recent progress on action recognition has mainly focused on RGB and optical flow features. In this paper, we approach the problem of joint-based action recognition. Unlike other modalities, constellation of joints and their motion generate models with succinct human motion information for activity recognition. We present a new model for joint-based action recognition, which first extracts motion features from each joint separately through a shared motion encoder before performing collective reasoning. Our joint selector module re-weights the joint information to select the most discriminative joints for the task. We also propose a novel joint-contrastive loss that pulls together groups of joint features which convey the same action. We strengthen the joint-based representations by using a geometry-aware data augmentation technique which jitters pose heatmaps while retaining the dynamics of the action. We show large improvements over the current state-of-the-art joint-based approaches on JHMDB, HMDB, Charades, AVA action recognition datasets. A late fusion with RGB and Flow-based approaches yields additional improvements. Our model also outperforms the existing baseline on Mimetics, a dataset with out-of-context actions.","url_abs":"https://arxiv.org/abs/2010.08164v2","url_pdf":"https://arxiv.org/pdf/2010.08164v2.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":"pose-and-joint-aware-action-recognition","repo_url":"https://github.com/anshulbshah/PoseAction","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":null,"task_name":"Action Recognition on HMDB-51"},{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"JMRN + R101-NL-LFB","rank_in_archive_order":23,"of":49,"metrics":{"MAP":"43.23"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"JMRN (Pose only)","rank_in_archive_order":49,"of":49,"metrics":{"MAP":"16.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ava-v21","task":"Action Recognition","dataset":"AVA v2.1","model":"JMRN + SlowFast-R101-NL","rank_in_archive_order":3,"of":15,"metrics":{"mAP (Val)":"28.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"Ours + ResNext101 BERT","rank_in_archive_order":8,"of":77,"metrics":{"Average accuracy of 3 splits":"84.53"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"JRMN","rank_in_archive_order":73,"of":77,"metrics":{"Average accuracy of 3 splits":"54.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-mimetics","task":"Action Recognition","dataset":"Mimetics","model":"JMRN","rank_in_archive_order":1,"of":2,"metrics":{"mAP":"40"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-mimetics","task":"Action Recognition","dataset":"Mimetics","model":"SIP-Net","rank_in_archive_order":2,"of":2,"metrics":{"mAP":"38.3"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-jhmdb-2d","task":"Skeleton Based Action Recognition","dataset":"JHMDB (2D poses only)","model":"JMRN (No GT pose)","rank_in_archive_order":3,"of":6,"metrics":{"Average accuracy of 3 splits":"68.55"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.08164","atlas_url":"https://app.syntology.ai/?focus=2010.08164","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2010.08164"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2010.08164\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2010.08164"},"call":"get_concepts_for_paper(arxiv_id=\"2010.08164\")"}],"by_repo":[{"repo":"anshulbshah/PoseAction","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cb6c8d53fed19d6776479c34897b3fb6291161e2c16cd4161fb9620e23992412","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}