{"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/vertex-feature-encoding-and-hierarchical","title":"Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition","arxiv_id":"1912.09745","date":"2019-12-20","proceeding":null,"authors":["Konstantinos Papadopoulos","Enjie Ghorbel","Djamila Aouada","Björn Ottersten"],"abstract":"This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D-60 and NTU RGB-D 120 datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.","url_abs":"https://arxiv.org/abs/1912.09745v1","url_pdf":"https://arxiv.org/pdf/1912.09745v1.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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgbd-120","task":"Action Recognition","dataset":"NTU RGB+D 120","model":"ST-GCN + AS-GCN w/DH-TCN","rank_in_archive_order":17,"of":21,"metrics":{"Accuracy (Cross-Setup)":"78.3","Accuracy (Cross-Subject)":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"GVFE + AS-GCN with DH-TCN","rank_in_archive_order":93,"of":135,"metrics":{"Accuracy (CS)":"85.3","Accuracy (CV)":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D 120","model":"GVFE + AS-GCN with DH-TCN","rank_in_archive_order":64,"of":83,"metrics":{"Accuracy (Cross-Setup)":"79.8%","Accuracy (Cross-Subject)":"78.3%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}