{"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/part-based-graph-convolutional-network-for","title":"Part-based Graph Convolutional Network for Action Recognition","arxiv_id":"1809.04983","date":"2018-09-13","proceeding":null,"authors":["Kalpit Thakkar","P. J. Narayanan"],"abstract":"Human actions comprise of joint motion of articulated body parts or\n`gestures'. Human skeleton is intuitively represented as a sparse graph with\njoints as nodes and natural connections between them as edges. Graph\nconvolutional networks have been used to recognize actions from skeletal\nvideos. We introduce a part-based graph convolutional network (PB-GCN) for this\ntask, inspired by Deformable Part-based Models (DPMs). We divide the skeleton\ngraph into four subgraphs with joints shared across them and learn a\nrecognition model using a part-based graph convolutional network. We show that\nsuch a model improves performance of recognition, compared to a model using\nentire skeleton graph. Instead of using 3D joint coordinates as node features,\nwe show that using relative coordinates and temporal displacements boosts\nperformance. Our model achieves state-of-the-art performance on two challenging\nbenchmark datasets NTURGB+D and HDM05, for skeletal action recognition.","url_abs":"http://arxiv.org/abs/1809.04983v1","url_pdf":"http://arxiv.org/pdf/1809.04983v1.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":"part-based-graph-convolutional-network-for","repo_url":"https://github.com/kalpitthakkar/pb-gcn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"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-recognition-in-videos-on-ntu-rgbd","task":"Action Recognition","dataset":"NTU RGB+D","model":"PB-GCN (Skeleton only)","rank_in_archive_order":25,"of":28,"metrics":{"Accuracy (CS)":"87.5","Accuracy (CV)":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"PB-GCN","rank_in_archive_order":75,"of":135,"metrics":{"Accuracy (CS)":"87.5","Accuracy (CV)":"93.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.04983","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}