{"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/revealing-key-details-to-see-differences-a","title":"Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition","arxiv_id":"2411.18941","date":"2024-11-28","proceeding":"CVPR 2025 1","authors":["Hongda Liu","Yunfan Liu","Min Ren","Hao Wang","Yunlong Wang","Zhenan Sun"],"abstract":"In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal representations. Recognizing that the differentiation of similar actions relies on subtle motion details in specific body parts, we direct our approach to focus on the fine-grained motion of local skeleton components. To this end, we introduce ProtoGCN, a Graph Convolutional Network (GCN)-based model that breaks down the dynamics of entire skeleton sequences into a combination of learnable prototypes representing core motion patterns of action units. By contrasting the reconstruction of prototypes, ProtoGCN can effectively identify and enhance the discriminative representation of similar actions. Without bells and whistles, ProtoGCN achieves state-of-the-art performance on multiple benchmark datasets, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, and FineGYM, which demonstrates the effectiveness of the proposed method. The code is available at https://github.com/firework8/ProtoGCN.","url_abs":"https://arxiv.org/abs/2411.18941v1","url_pdf":"https://arxiv.org/pdf/2411.18941v1.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":"revealing-key-details-to-see-differences-a","repo_url":"https://github.com/firework8/ProtoGCN","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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/skeleton-based-action-recognition-on-kinetics","task":"Skeleton Based Action Recognition","dataset":"Kinetics-Skeleton dataset","model":"ProtoGCN","rank_in_archive_order":2,"of":42,"metrics":{"Accuracy":"51.9"},"uses_additional_data":true},{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd","task":"Skeleton Based Action Recognition","dataset":"NTU RGB+D","model":"ProtoGCN","rank_in_archive_order":5,"of":135,"metrics":{"Accuracy (CS)":"93.8","Accuracy (CV)":"97.8","Ensembled Modalities":"6"},"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":"ProtoGCN","rank_in_archive_order":1,"of":83,"metrics":{"Accuracy (Cross-Setup)":"92.2","Accuracy (Cross-Subject)":"90.9","Ensembled Modalities":"6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.18941","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}