{"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/compact-generalized-non-local-network","title":"Compact Generalized Non-local Network","arxiv_id":"1810.13125","date":"2018-10-31","proceeding":"NeurIPS 2018 12","authors":["Kaiyu Yue","Ming Sun","Yuchen Yuan","Feng Zhou","Errui Ding","Fuxin Xu"],"abstract":"The non-local module is designed for capturing long-range spatio-temporal\ndependencies in images and videos. Although having shown excellent performance,\nit lacks the mechanism to model the interactions between positions across\nchannels, which are of vital importance in recognizing fine-grained objects and\nactions. To address this limitation, we generalize the non-local module and\ntake the correlations between the positions of any two channels into account.\nThis extension utilizes the compact representation for multiple kernel\nfunctions with Taylor expansion that makes the generalized non-local module in\na fast and low-complexity computation flow. Moreover, we implement our\ngeneralized non-local method within channel groups to ease the optimization.\nExperimental results illustrate the clear-cut improvements and practical\napplicability of the generalized non-local module on both fine-grained object\nrecognition and video classification. Code is available at:\nhttps://github.com/KaiyuYue/cgnl-network.pytorch.","url_abs":"http://arxiv.org/abs/1810.13125v2","url_pdf":"http://arxiv.org/pdf/1810.13125v2.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":"compact-generalized-non-local-network","repo_url":"https://github.com/KaiyuYue/cgnl-network.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"compact-generalized-non-local-network","repo_url":"https://github.com/NUAAXQ/MLCVNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.13125","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}