{"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/stand-alone-inter-frame-attention-in-video-1","title":"Stand-Alone Inter-Frame Attention in Video Models","arxiv_id":"2206.06931","date":"2022-06-14","proceeding":"CVPR 2022 1","authors":["Fuchen Long","Zhaofan Qiu","Yingwei Pan","Ting Yao","Jiebo Luo","Tao Mei"],"abstract":"Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-temporal 3D convolutions, factorizing 3D convolutions into spatial and temporal convolutions separately, or computing self-attention along temporal dimension. The implicit assumption behind such successes is that the feature maps across consecutive frames can be nicely aggregated. Nevertheless, the assumption may not always hold especially for the regions with large deformation. In this paper, we present a new recipe of inter-frame attention block, namely Stand-alone Inter-Frame Attention (SIFA), that novelly delves into the deformation across frames to estimate local self-attention on each spatial location. Technically, SIFA remoulds the deformable design via re-scaling the offset predictions by the difference between two frames. Taking each spatial location in the current frame as the query, the locally deformable neighbors in the next frame are regarded as the keys/values. Then, SIFA measures the similarity between query and keys as stand-alone attention to weighted average the values for temporal aggregation. We further plug SIFA block into ConvNets and Vision Transformer, respectively, to devise SIFA-Net and SIFA-Transformer. Extensive experiments conducted on four video datasets demonstrate the superiority of SIFA-Net and SIFA-Transformer as stronger backbones. More remarkably, SIFA-Transformer achieves an accuracy of 83.1% on Kinetics-400 dataset. Source code is available at \\url{https://github.com/FuchenUSTC/SIFA}.","url_abs":"https://arxiv.org/abs/2206.06931v1","url_pdf":"https://arxiv.org/pdf/2206.06931v1.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":"stand-alone-inter-frame-attention-in-video-1","repo_url":"https://github.com/fuchenustc/sifa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sifa","method_name":"SIFA"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"SIFA","rank_in_archive_order":70,"of":207,"metrics":{"Acc@1":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"SIFA","rank_in_archive_order":14,"of":74,"metrics":{"Top 1 Accuracy":"57.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"SIFA","rank_in_archive_order":42,"of":123,"metrics":{"Top-1 Accuracy":"69.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.06931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}