{"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/revisiting-temporal-modeling-for-video-based","title":"Revisiting Temporal Modeling for Video-based Person ReID","arxiv_id":"1805.02104","date":"2018-05-05","proceeding":null,"authors":["Jiyang Gao","Ram Nevatia"],"abstract":"Video-based person reID is an important task, which has received much\nattention in recent years due to the increasing demand in surveillance and\ncamera networks. A typical video-based person reID system consists of three\nparts: an image-level feature extractor (e.g. CNN), a temporal modeling method\nto aggregate temporal features and a loss function. Although many methods on\ntemporal modeling have been proposed, it is hard to directly compare these\nmethods, because the choice of feature extractor and loss function also have a\nlarge impact on the final performance. We comprehensively study and compare\nfour different temporal modeling methods (temporal pooling, temporal attention,\nRNN and 3D convnets) for video-based person reID. We also propose a new\nattention generation network which adopts temporal convolution to extract\ntemporal information among frames. The evaluation is done on the MARS dataset,\nand our methods outperform state-of-the-art methods by a large margin. Our\nsource codes are released at https://github.com/jiyanggao/Video-Person-ReID.","url_abs":"http://arxiv.org/abs/1805.02104v2","url_pdf":"http://arxiv.org/pdf/1805.02104v2.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":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/jiyanggao/Video-Person-ReID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/Allen-lz/Video-Person-ReID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/HoganZhang/Video-Person-ReID-temporal-modeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/InnovArul/vidreid_cosegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/Proxim123/person-re-id","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/mattcoldwater/Video-ReID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/ppriyank/Video-Person-Re-ID-Fantastic-Techniques-and-Where-to-Find-Them","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-temporal-modeling-for-video-based","repo_url":"https://github.com/pretendwh/Revisiting-temporal-modeling-for-video-based-person-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02104","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}