{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:47:20Z","timestamp":1775540840661,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20241202130548062"],"award-info":[{"award-number":["JCYJ20241202130548062"]}]},{"name":"Natural Science Foundation of Shenzhen","award":["JCYJ20230807142703006"],"award-info":[{"award-number":["JCYJ20230807142703006"]}]},{"name":"Guangdong Provincial Key Area Project of General Universities","award":["2024ZDZX1017"],"award-info":[{"award-number":["2024ZDZX1017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651051","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"2391-2403","source":"Crossref","is-referenced-by-count":0,"title":["Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1539-7167","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4424-4352","authenticated-orcid":false,"given":"Zhi","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6955-4170","authenticated-orcid":false,"given":"Qingjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"ref3","article-title":"Generalizing across domains via cross-gradient training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shankar","year":"2018"},{"key":"ref4","first-page":"7313","article-title":"Domain generalization using causal matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mahajan","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00858"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01439"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26351-4_35"},{"key":"ref10","article-title":"Domain-unified prompt representations for source-free domain generalization","author":"Niu","year":"2022"},{"key":"ref11","first-page":"13678","article-title":"A closer look at the robustness of contrastive language-image pre-training (CLIP)","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Tu","year":"2023"},{"key":"ref12","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3547916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382493"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377136"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref18","article-title":"Toast: Transfer learning via attention steering","volume":"5","author":"Shi","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106281"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01257"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25984"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46147-8_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00726"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref28","article-title":"Gradient matching for domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref29","first-page":"4010","article-title":"DNA: Domain generalization with diversified neural averaging","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00367"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","article-title":"A hard-to-beat baseline for training-free CLIP-based adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28316"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02227"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref37","article-title":"Captions are worth a thousand words: Enhancing product retrieval with pretrained image-to-text models","volume-title":"Proc. 3rd Int. Workshop Interactive Scalable Inf. Retr. Methods E-Commerce (ISIR-eCom)","author":"Tang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28466"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"ref40","article-title":"Linearly mapping from image to text space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Merullo","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02322-1"},{"key":"ref42","article-title":"Amortized prompt: Lightweight finetuning for clip in domain generalization","author":"Zhang","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00545"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref45","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref50","article-title":"Tell your model where to attend: Post-hoc attention steering for llms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/760"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_19"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.208"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref62","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_25"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref65","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_26"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_15"},{"key":"ref71","first-page":"4267","article-title":"Clipceil: Domain generalization through clip via channel refinement and image-text alignment","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Yu","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"ref73","article-title":"Robust and generalizable visual representation learning via random convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01539"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329507.pdf?arnumber=11329507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:51:47Z","timestamp":1775537507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651051","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}