{"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/self-attention-network-for-skeleton-based","title":"Self-Attention Network for Skeleton-based Human Action Recognition","arxiv_id":"1912.08435","date":"2019-12-18","proceeding":null,"authors":["Sangwoo Cho","Muhammad Hasan Maqbool","Fei Liu","Hassan Foroosh"],"abstract":"Skeleton-based action recognition has recently attracted a lot of attention. Researchers are coming up with new approaches for extracting spatio-temporal relations and making considerable progress on large-scale skeleton-based datasets. Most of the architectures being proposed are based upon recurrent neural networks (RNNs), convolutional neural networks (CNNs) and graph-based CNNs. When it comes to skeleton-based action recognition, the importance of long term contextual information is central which is not captured by the current architectures. In order to come up with a better representation and capturing of long term spatio-temporal relationships, we propose three variants of Self-Attention Network (SAN), namely, SAN-V1, SAN-V2 and SAN-V3. Our SAN variants has the impressive capability of extracting high-level semantics by capturing long-range correlations. We have also integrated the Temporal Segment Network (TSN) with our SAN variants which resulted in improved overall performance. Different configurations of Self-Attention Network (SAN) variants and Temporal Segment Network (TSN) are explored with extensive experiments. Our chosen configuration outperforms state-of-the-art Top-1 and Top-5 by 4.4% and 7.9% respectively on Kinetics and shows consistently better performance than state-of-the-art methods on NTU RGB+D.","url_abs":"https://arxiv.org/abs/1912.08435v1","url_pdf":"https://arxiv.org/pdf/1912.08435v1.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"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"TS-SAN","rank_in_archive_order":77,"of":135,"metrics":{"Accuracy (CS)":"87.2","Accuracy (CV)":"92.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.08435","atlas_url":"https://app.syntology.ai/?focus=1912.08435","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}