{"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/region-based-non-local-operation-for-video","title":"Region-based Non-local Operation for Video Classification","arxiv_id":"2007.09033","date":"2020-07-17","proceeding":null,"authors":["Guoxi Huang","Adrian G. Bors"],"abstract":"Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult. This paper presents region-based non-local (RNL) operations as a family of self-attention mechanisms, which can directly capture long-range dependencies without using a deep stack of local operations. Given an intermediate feature map, our method recalibrates the feature at a position by aggregating the information from the neighboring regions of all positions. By combining a channel attention module with the proposed RNL, we design an attention chain, which can be integrated into the off-the-shelf CNNs for end-to-end training. We evaluate our method on two video classification benchmarks. The experimental results of our method outperform other attention mechanisms, and we achieve state-of-the-art performance on the Something-Something V1 dataset.","url_abs":"https://arxiv.org/abs/2007.09033v5","url_pdf":"https://arxiv.org/pdf/2007.09033v5.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":"region-based-non-local-operation-for-video","repo_url":"https://github.com/guoxih/region-based-non-local-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Position"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"RNL+TSM Ensemble(ResNet50, 8 + 16 frames)","rank_in_archive_order":141,"of":207,"metrics":{"Acc@1":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"RNL+TSM Ensemble(R50+R101, ImageNet pretrained)","rank_in_archive_order":33,"of":74,"metrics":{"Top 1 Accuracy":"54.1","Top 5 Accuracy":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"RNL+TSM Ensemble(ResNet50, ImageNet pretrained)","rank_in_archive_order":40,"of":74,"metrics":{"Top 1 Accuracy":"52.7","Top 5 Accuracy":"81.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.09033","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}