{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:54:43Z","timestamp":1762368883681,"version":"build-2065373602"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222207","62427808","62306142"],"award-info":[{"award-number":["62222207","62427808","62306142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3617294","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T17:42:39Z","timestamp":1759426959000},"page":"4049-4053","source":"Crossref","is-referenced-by-count":0,"title":["SODA: Structural Pre-Decoupling and Co-Aligning for Video Compositional Representation"],"prefix":"10.1109","volume":"32","author":[{"given":"Peng","family":"Huang","sequence":"first","affiliation":[{"name":"College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghao","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2690339"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3456670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3358755"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020076"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00921"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"article-title":"Interactive fusion of multi-level features for compositional activity recognition","year":"2020","author":"Yan","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3384392"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3341297"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547862"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_21"},{"article-title":"UniFormerV2: Spatiotemporal learning by arming image ViTs with video UniFormer","year":"2022","author":"Li","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref26","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Patrick","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"article-title":"Learning clustering-based prototypes for compositional zero-shot learning","year":"2025","author":"Qu","key":"ref33"},{"article-title":"Roberta: A robustly optimized BERT pretraining approach","year":"2019","author":"Liu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11190001.pdf?arnumber=11190001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:44:00Z","timestamp":1762368240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11190001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3617294","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}