{"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/multi-view-action-recognition-using","title":"Multi-View Action Recognition Using Contrastive Learning","arxiv_id":null,"date":"2023-01-03","proceeding":"IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 1","authors":["Ketul Shah","Anshul Shah","Chun Pong Lau","Celso M. de Melo","Rama Chellappa"],"abstract":"In this work, we present a method for RGB-based action recognition using multi-view videos. We present a supervised contrastive learning framework to learn a feature embedding robust to changes in viewpoint, by effectively leveraging multi-view data. We use an improved supervised contrastive loss and augment the positives with those coming from synchronized viewpoints. We also propose a new approach to use classifier probabilities to guide the selection of hard negatives in the contrastive loss, to learn a more discriminative representation. Negative samples from confusing classes based on posterior are weighted higher. We also show that our method leads to better domain generalization compared to the standard supervised training based on synthetic multi-view data. Extensive experiments on real (NTU-60, NTU-120, NUMA) and synthetic (RoCoG) data demonstrate the effectiveness of our approach.","url_abs":"https://openaccess.thecvf.com/content/WACV2023/html/Shah_Multi-View_Action_Recognition_Using_Contrastive_Learning_WACV_2023_paper.html","url_pdf":"https://openaccess.thecvf.com/content/WACV2023/papers/Shah_Multi-View_Action_Recognition_Using_Contrastive_Learning_WACV_2023_paper.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":"multi-view-action-recognition-using","repo_url":"https://github.com/kshah33/viewcon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgbd","task":"Action Recognition","dataset":"NTU RGB+D","model":"ViewCon (RGB + Pose)","rank_in_archive_order":14,"of":28,"metrics":{"Accuracy (CS)":"93.7","Accuracy (CV)":"98.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgbd-120","task":"Action Recognition","dataset":"NTU RGB+D 120","model":"ViewCon (RGB)","rank_in_archive_order":15,"of":21,"metrics":{"Accuracy (Cross-Setup)":"87.5","Accuracy (Cross-Subject)":"85.6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}