{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T21:57:37Z","timestamp":1790978257546,"version":"4.1.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Key Project of PCL","award":["PCL2025AS10"],"award-info":[{"award-number":["PCL2025AS10"]}]},{"name":"Shenzhen Science and Technology Program","award":["RCJC20231211085918010"],"award-info":[{"award-number":["RCJC20231211085918010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3703017","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:42:29Z","timestamp":1781293349000},"page":"12906-12919","source":"Crossref","is-referenced-by-count":3,"title":["Negation-Aware Test-Time Adaptation for Vision-Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0479-8932","authenticated-orcid":false,"given":"Haochen","family":"Han","sequence":"first","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-9146","authenticated-orcid":false,"given":"Alex Jinpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8570-1345","authenticated-orcid":false,"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2388","authenticated-orcid":false,"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02258"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02757"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3506283"},{"key":"ref4","article-title":"Qwen3-VL technical report","author":"Zhou","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref7","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist., JMLR Workshop Conf. Proc.","author":"Coates","year":"2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/desc.13085"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3460180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01818"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2005.12.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref22","first-page":"5637","article-title":"Wilds: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3131"},{"key":"ref24","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref25","first-page":"1","article-title":"RA-TTA: Retrieval-augmented test-time adaptation for vision-language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Lee","year":"2025"},{"key":"ref26","first-page":"76517","article-title":"Test-time adaptation for cross-modal retrieval with query shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2025"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435790"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref32","first-page":"1","article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Niu","year":"2023"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref39","article-title":"Learn\u201d no\u201d to say\u201d yes\u201d better: Improving vision-language models via negations","author":"Singh","year":"2024"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.31234\/osf.io\/nfv4j","article-title":"Infants\u2019 early understanding of different forms of negation","author":"Szab\u00f3","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3343736"},{"key":"ref42","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01314"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref46","first-page":"1","article-title":"Test-time adaptation against multi-modal reliability bias","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref47","first-page":"1","article-title":"C-TPT: Calibrated test-time prompt tuning for vision-language models via text feature dispersion","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yoon","year":"2024"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1010"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref51","first-page":"3597","article-title":"Test-time adaptation with clip reward for zero-shot generalization in vision-language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhao","year":"2024"},{"key":"ref52","article-title":"Calling a spade a heart: Gaslighting multimodal large language models via negation","author":"Zhu","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11561105.pdf?arnumber=11561105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:40:05Z","timestamp":1790264405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11561105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":52,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3703017","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":[[2026,10]]}}}