{"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/temporal-3d-shape-modeling-for-video-based","title":"Temporal 3D Shape Modeling for Video-Based Cloth-Changing Person Re-Identification","arxiv_id":null,"date":"2024-01-04","proceeding":"IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops 2024 1","authors":["Vuong D. Nguyen","Pranav Mantini","Shishir K. Shah"],"abstract":"Video-based Cloth-Changing Person Re-ID (VCCRe-ID) refers to a real-world Re-ID problem where texture information like appearance or clothing becomes unreliable in long-term, limiting the applicability of traditional Re-ID methods. VCCRe-ID has not been well studied primarily due to (1) limited public datasets and (2) challenges related to extracting identity-related clothes-invariant cues from videos. Few existing works have heavily focused on gait-based features, which are severely affected under viewpoint changes and occlusions. In this work, we propose \"Temporal 3D ShapE Modeling for VCCRe-ID\" (SEMI), a lightweight end-to-end framework that addresses these issues by learning human 3D shape representations. The SEMI framework comprises of a Temporal 3D Shape Modeling branch, which extracts discriminative frame-wise 3D shape features using a temporal encoder, and an identity-aware 3D regressor. This is followed by a novel Attention-based Shape Aggregation (ASA) module that effectively aggregates frame-wise shape features for a fine-grained video-wise shape embedding. ASA leverages an attention mechanism to amplify the contribution of the most important frames while reducing redundancy during the aggregation process. Experiments on two VCCRe-ID datasets demonstrate that our proposed framework outperforms state-of-the-art methods by 10.7% in rank-1 accuracy and 7.4% in mAP in cloth-changing setting.","url_abs":"https://openaccess.thecvf.com/content/WACV2024W/RWS/html/Nguyen_Temporal_3D_Shape_Modeling_for_Video-Based_Cloth-Changing_Person_Re-Identification_WACVW_2024_paper.html","url_pdf":"https://openaccess.thecvf.com/content/WACV2024W/RWS/papers/Nguyen_Temporal_3D_Shape_Modeling_for_Video-Based_Cloth-Changing_Person_Re-Identification_WACVW_2024_paper.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":"temporal-3d-shape-modeling-for-video-based","repo_url":"https://github.com/dustin-nguyen-qil/SEMI_VCCReID","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"temporal-3d-shape-modeling-for-video-based","repo_url":"https://github.com/dustin-nguyen-qil/Videobased-ClothChanging-ReID-Baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-shape-modeling","task_name":"3D Shape Modeling"},{"task_slug":"cloth-changing-person-re-identification","task_name":"Cloth-Changing Person Re-Identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}