{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T14:28:27Z","timestamp":1770733707597,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFC3308400"],"award-info":[{"award-number":["2024YFC3308400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176188"],"award-info":[{"award-number":["62176188"]}],"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":["62361166629"],"award-info":[{"award-number":["62361166629"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Science and Technology Innovation of Hubei Province","award":["2024BCA003"],"award-info":[{"award-number":["2024BCA003"]}]},{"name":"Major Project of Science and Technology Innovation of Hubei Province","award":["2025BEA002"],"award-info":[{"award-number":["2025BEA002"]}]},{"name":"NTU RSR"},{"name":"Start Up Grants"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3634165","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T18:45:20Z","timestamp":1763491520000},"page":"3119-3136","source":"Crossref","is-referenced-by-count":0,"title":["Synergy of Sight and Semantics: Holistic Visual Understanding With CLIP"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5397-0209","authenticated-orcid":false,"given":"Qu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532430"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/2053951719897945"},{"key":"ref10","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kiela"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.wnsx.2021.100103"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2196\/17187"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref15","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref16","article-title":"Adaptive re-calibration learning for balanced multimodal intention recognition","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3247876"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3234817"},{"key":"ref19","article-title":"EmoLLM: Multimodal emotional understanding meets large language models","author":"Yang","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02300"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3568519"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007352"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00834"},{"key":"ref26","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"},{"key":"ref27","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562999"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3561366"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3548704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3558854"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref35","first-page":"30569","article-title":"DualCoOp: Fast adaptation to multi-label recognition with limited annotations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346405"},{"key":"ref37","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022"},{"key":"ref38","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref40","article-title":"Tip-Adapter: Training-free clip-adapter for better vision-language modeling","author":"Zhang","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","article-title":"Query2label: A simple transformer way to multi-label classification","author":"Liu","year":"2021"},{"key":"ref44","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref48","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref49","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref51","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref52","first-page":"10150","article-title":"MultiGuard: Provably robust multi-label classification against adversarial examples","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261743"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3380250"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93046-2_47"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.062"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_37"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00105"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00603"},{"key":"ref61","article-title":"Grad-cam: Why did you say that?","author":"Selvaraju","year":"2016"},{"key":"ref62","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023"},{"key":"ref63","first-page":"15028","article-title":"CLIPLoss and norm-based data selection methods for multimodal contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref65","article-title":"TULIP: Towards unified language-image pretraining","author":"Tang","year":"2025"},{"key":"ref66","article-title":"Grad-ECLIP: Gradient-based visual and textual explanations for clip","author":"Zhao","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11251254.pdf?arnumber=11251254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:25Z","timestamp":1770671125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11251254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3634165","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}