{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:46Z","timestamp":1777888786855,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00154","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1569-1579","source":"Crossref","is-referenced-by-count":0,"title":["BATCLIP: Bimodal Online Test-Time Adaptation for CLIP"],"prefix":"10.1109","author":[{"given":"Sarthak Kumar","family":"Maharana","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoming","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonid","family":"Karlinsky","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhui","family":"Guo","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref2","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume":"35","author":"Bangalath","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_26"},{"key":"ref7","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"Cuturi","year":"2013","journal-title":"Advances in neural information processing systems, 26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00744"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_8"},{"key":"ref11","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.208"},{"key":"ref13","author":"Goodfellow","year":"2013","journal-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211"},{"key":"ref14","article-title":"In search of lost domain generalization","author":"Gulrajani","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Clipartt: Light-weight adaptation of clip to new domains at test time","author":"Adolfo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref21","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref22","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2016","journal-title":"arXiv preprint"},{"key":"ref23","author":"Li","year":"2022","journal-title":"Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref25","article-title":"Revisiting batch normalization for practical domain adaptation","author":"Li","year":"2016","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112187"},{"key":"ref27","article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"International Conference on Machine Learning, pages 2303323044. PMLR","author":"Luo","year":"2023"},{"key":"ref28","article-title":"Swapprompt: Test-time prompt adaptation for visionlanguage models","author":"Ma","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"ref31","article-title":"Words matter: Leveraging individual text embeddings for code generation in clip testtime adaptation","author":"Mishra","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"International Conference on Machine Learning, pages 1688816905. PMLR","author":"Niu","year":"2022"},{"key":"ref33","article-title":"Watt: Weight average test-time adaption of clip","author":"Osowiechi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"issue":"2","key":"ref35","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","article-title":"If your data distribution shifts, use selflearning","author":"Rusak","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref39","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume":"33","author":"Schneider","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref43","article-title":"Test-time training with selfsupervision for generalization under distribution shifts","volume-title":"International Conference on Machine Learning, pages 92299248. PMLR","author":"Sun","year":"2020"},{"issue":"11","key":"ref44","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref45","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref48","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01528"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02337"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1988"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2799"},{"key":"ref53","article-title":"Tuning layernorm in attention: Towards efficient multi-modal 11 m finetuning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Test-time adaptation with clip reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446054.pdf?arnumber=11446054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:10Z","timestamp":1777611490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00154","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}