{"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/motion-representation-using-residual-frames","title":"Motion Representation Using Residual Frames with 3D CNN","arxiv_id":"2006.13017","date":"2020-06-21","proceeding":null,"authors":["Li Tao","Xueting Wang","Toshihiko Yamasaki"],"abstract":"Recently, 3D convolutional networks (3D ConvNets) yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets. By replacing traditional stacked RGB frames with residual ones, 35.6% and 26.6% points improvements over top-1 accuracy can be obtained on the UCF101 and HMDB51 datasets when ResNet-18 models are trained from scratch. And we achieved the state-of-the-art results in this training mode. Analysis shows that better motion features can be extracted using residual frames compared to RGB counterpart. By combining with a simple appearance path, our proposal can be even better than some methods using optical flow streams.","url_abs":"https://arxiv.org/abs/2006.13017v1","url_pdf":"https://arxiv.org/pdf/2006.13017v1.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":"motion-representation-using-residual-frames","repo_url":"https://github.com/BestJuly/IIC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"motion-representation-using-residual-frames","repo_url":"https://github.com/BestJuly/Inter-intra-video-contrastive-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"motion-representation-using-residual-frames","repo_url":"https://github.com/BestJuly/VCP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}