{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:59:03Z","timestamp":1730303943506,"version":"3.28.0"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017567","name":"Apple","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,3]]},"DOI":"10.1109\/wacv57701.2024.00267","type":"proceedings-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:36:09Z","timestamp":1712684169000},"page":"2679-2689","source":"Crossref","is-referenced-by-count":2,"title":["Empowering Unsupervised Domain Adaptation with Large-scale Pre-trained Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Zhengfeng","family":"Lai","sequence":"first","affiliation":[{"name":"University of California,Davis"}]},{"given":"Haoping","family":"Bai","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]},{"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]},{"given":"Xianzhi","family":"Du","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]},{"given":"Jiulong","family":"Shan","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]},{"given":"Yinfei","family":"Yang","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]},{"given":"Chen-Nee","family":"Chuah","sequence":"additional","affiliation":[{"name":"University of California,Davis"}]},{"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"Apple AI\/ML"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.24963\/ijcai.2019\/285"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR52729.2023.02283"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR52688.2022.00704"},{"volume-title":"ICML","author":"Chen","article-title":"Learning domain adaptive object detection with probabilistic teacher","key":"ref4"},{"key":"ref5","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"ICML","author":"Chen"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.48550\/ARXIV.1604.01685"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR46437.2021.00729"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR52729.2023.02282"},{"volume-title":"ICLR","author":"Dosovitskiy","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","key":"ref10"},{"key":"ref11","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"ICML","author":"Ganin"},{"key":"ref12","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"JMLR"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-030-58592-1_35"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/s11263-023-01891-x"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICCV48922.2021.00881"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/tnnls.2023.3327962"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref18","article-title":"Generative adversarial networks","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR52729.2023.01853"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR52729.2023.01128"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR52688.2022.00127"},{"year":"2022","author":"Huang","article-title":"Unsupervised prompt learning for vision-language models","key":"ref23"},{"key":"ref24","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia"},{"volume-title":"ICLR","author":"Kang","article-title":"Decoupling representation and classifier for long-tailed recognition","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2019.00503"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCV51070.2023.01480"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TPAMI.2020.2991050"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR52688.2022.01069"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TIP.2018.2839528"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/CVPR46437.2021.01135"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICCV48922.2021.00897"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR52688.2022.00522"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR52688.2022.00743"},{"key":"ref35","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","volume-title":"ICML","author":"Liang"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","first-page":"1645","article-title":"Conditional adversarial domain adaptation","volume-title":"NeurIPS","author":"Long"},{"key":"ref38","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"ICML","author":"Long"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR52688.2022.00514"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/CVPR42600.2020.00913"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1007\/978-3-031-19809-0_30"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ICCV.2019.00149"},{"year":"2017","author":"Peng","article-title":"Visda: The visual domain adaptation challenge","key":"ref43"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref45","first-page":"18378","article-title":"A closer look at smoothness in domain adversarial training","volume-title":"ICML","author":"Rangwani"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1007\/978-3-642-15561-1_16"},{"author":"Sahoo","journal-title":"Frustratingly simple contrastive prompt tuning for vision-language models","key":"ref47"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref49","first-page":"14274","article-title":"Testtime prompt tuning for zero-shot generalization in vision-language models","volume":"35","author":"Shu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1007\/978-3-031-19827-4_37"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR52688.2022.00705"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/CVPR42600.2020.00875"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1109\/CVPR.2017.572"},{"volume-title":"NeurIPS","author":"Wang","article-title":"Transferable normalization: Towards improving transferability of deep neural networks","key":"ref56"},{"key":"ref57","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An occam\u2019s razor for domain incremental learning","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/ICCV.2019.00041"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1109\/TPAMI.2022.3174526"},{"volume-title":"ICLR","author":"Xu","article-title":"Cdtrans: Cross-domain transformer for unsupervised domain adaptation","key":"ref60"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/WACV56688.2023.00059"},{"key":"ref62","article-title":"Attracting and dispersing: A simple approach for source-free domain adaptation","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1007\/978-3-031-19827-4_40"},{"year":"2022","author":"Yu","journal-title":"Coca: Contrastive captioners are image-text foundation models","key":"ref64"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/CVPR52729.2023.01049"},{"year":"2021","author":"Yuan","journal-title":"Florence: A new foundation model for computer vision","key":"ref66"},{"doi-asserted-by":"publisher","key":"ref67","DOI":"10.1109\/CVPR52688.2022.01179"},{"doi-asserted-by":"publisher","key":"ref68","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref69","first-page":"18408","article-title":"Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume":"34","author":"Zhang","year":"2021","journal-title":"NeurIPS"},{"key":"ref70","first-page":"36067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref71","DOI":"10.1109\/CVPR52688.2022.00960"},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref73","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","volume-title":"ICML","author":"Zhang"},{"doi-asserted-by":"publisher","key":"ref74","DOI":"10.1109\/CVPR52688.2022.01382"},{"doi-asserted-by":"publisher","key":"ref75","DOI":"10.1109\/CVPR52688.2022.01631"},{"doi-asserted-by":"publisher","key":"ref76","DOI":"10.1007\/s11263-022-01653-1"},{"doi-asserted-by":"publisher","key":"ref77","DOI":"10.1109\/CVPR52688.2022.00936"},{"doi-asserted-by":"publisher","key":"ref78","DOI":"10.1109\/CVPR52729.2023.00347"}],"event":{"name":"2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","start":{"date-parts":[[2024,1,3]]},"location":"Waikoloa, HI, USA","end":{"date-parts":[[2024,1,8]]}},"container-title":["2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10483279\/10483282\/10484237.pdf?arnumber=10484237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T17:25:03Z","timestamp":1713201903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10484237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/wacv57701.2024.00267","relation":{},"subject":[],"published":{"date-parts":[[2024,1,3]]}}}