{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:12:54Z","timestamp":1778530374971,"version":"3.51.4"},"reference-count":46,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422607"],"award-info":[{"award-number":["62422607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372411"],"award-info":[{"award-number":["62372411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036009"],"award-info":[{"award-number":["62036009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432014"],"award-info":[{"award-number":["62432014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406287"],"award-info":[{"award-number":["62406287"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LR23F020003"],"award-info":[{"award-number":["LR23F020003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3660158","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:45:03Z","timestamp":1770065103000},"page":"3471-3486","source":"Crossref","is-referenced-by-count":0,"title":["CompoVis: Is Cross-Modal Semantic Alignment of CLIP Optimal? A Visual Analysis Attempt"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4642-9932","authenticated-orcid":false,"given":"Tong","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8383-8153","authenticated-orcid":false,"given":"Guodao","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2255-9182","authenticated-orcid":false,"given":"Xueqian","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2732-1571","authenticated-orcid":false,"given":"Qi","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4341-3028","authenticated-orcid":false,"given":"Wang","family":"Xia","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7378-9245","authenticated-orcid":false,"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1349-0774","authenticated-orcid":false,"given":"Haidong","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2378-2725","authenticated-orcid":false,"given":"Haixia","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-9608","authenticated-orcid":false,"given":"Ronghua","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3138933"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.143"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327168"},{"key":"ref7","article-title":"Evaluating compositional scene understanding in multimodal generative models","author":"Fu","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368922"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1568"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02314"},{"key":"ref15","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2024.3409722"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3434373"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3261935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3388514"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864838"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12650-021-00803-w"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3225114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02821"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3423402"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3417694"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399075"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521709"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0393-x"},{"key":"ref38","article-title":"The dawn of LLMs: Preliminary explorations with GPT-4V (ISION)","author":"Yang","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456387"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327163"},{"key":"ref41","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref42","first-page":"1","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yuksekgonul","year":"2023"},{"key":"ref43","article-title":"Understanding and mitigating compositional issues in text-to-image generative models","author":"Zarei","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01341"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW60847.2023.00023"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11370253.pdf?arnumber=11370253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:47:12Z","timestamp":1778528832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11370253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3660158","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}