{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:31:39Z","timestamp":1790703099355,"version":"4.1.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100015651","name":"Safran SA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015651","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.cviu.2026.104721","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:52:20Z","timestamp":1773273140000},"page":"104721","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Text-Aided Domain Adaptation for CLIP-like models and application to challenging domain shifts"],"prefix":"10.1016","volume":"267","author":[{"given":"Louis","family":"H\u00e9madou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H\u00e9l\u00e9na","family":"Vorobieva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ewa","family":"Kijak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Jurie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104721_b1","series-title":"Llama 3 model card","author":"AI@Meta","year":"2024"},{"key":"10.1016\/j.cviu.2026.104721_b2","doi-asserted-by":"crossref","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","author":"Ben-David","year":"2010","journal-title":"Mach. Learn."},{"key":"10.1016\/j.cviu.2026.104721_b3","article-title":"StyLIP: Multi-scale style-conditioned prompt learning for CLIP-based domain generalization","author":"Bose","year":"2023","journal-title":"WACV"},{"key":"10.1016\/j.cviu.2026.104721_b4","doi-asserted-by":"crossref","unstructured":"Cherti,\u00a0M., Beaumont,\u00a0R., Wightman,\u00a0R., Wortsman,\u00a0M., Ilharco,\u00a0G., Gordon,\u00a0C., Schuhmann,\u00a0C., Schmidt,\u00a0L., Jitsev,\u00a0J., 2023. Reproducible Scaling Laws for Contrastive Language-Image Learning. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"10.1016\/j.cviu.2026.104721_b5","doi-asserted-by":"crossref","unstructured":"Cho,\u00a0J., Nam,\u00a0G., Kim,\u00a0S., Yang,\u00a0H., Kwak,\u00a0S., 2023. PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization. In: ICCV.","DOI":"10.1109\/ICCV51070.2023.01439"},{"key":"10.1016\/j.cviu.2026.104721_b6","unstructured":"Dunlap,\u00a0L., Mohri,\u00a0C., Guillory,\u00a0D., Zhang,\u00a0H., Darrell,\u00a0T., Gonzalez,\u00a0J.E., Raghunathan,\u00a0A., Rohrbach,\u00a0A., 2023. Using Language to Extend to Unseen Domains. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104721_b7","doi-asserted-by":"crossref","unstructured":"Fahes,\u00a0M., Vu,\u00a0T., Bursuc,\u00a0A., P\u00e9rez,\u00a0P., de Charette,\u00a0R., 2023. P\u00d8DA: Prompt-driven Zero-shot Domain Adaptation. In: ICCV.","DOI":"10.1109\/ICCV51070.2023.01707"},{"key":"10.1016\/j.cviu.2026.104721_b8","series-title":"A simple recipe for language-guided domain generalized segmentation","author":"Fahes","year":"2024"},{"key":"10.1016\/j.cviu.2026.104721_b9","unstructured":"Fang,\u00a0A., Jose,\u00a0A.M., Jain,\u00a0A., Schmidt,\u00a0L., Toshev,\u00a0A.T., Shankar,\u00a0V., 2024. Data Filtering Networks. In: The Twelfth International Conference on Learning Representations. ICLR 2024, Vienna, Austria, May 7\u201311, 2024."},{"key":"10.1016\/j.cviu.2026.104721_b10","article-title":"StyleGAN-NADA: CLIP-guided domain adaptation of image generators","author":"Gal","year":"2022","journal-title":"ACM"},{"key":"10.1016\/j.cviu.2026.104721_b11","article-title":"Domain-adversarial training of neural networks","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cviu.2026.104721_b12","unstructured":"Gulrajani,\u00a0I., Lopez-Paz,\u00a0D., 2021. In Search of Lost Domain Generalization. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104721_b13","unstructured":"Jia,\u00a0C., Yang,\u00a0Y., Xia,\u00a0Y., Chen,\u00a0Y., Parekh,\u00a0Z., Pham,\u00a0H., Le,\u00a0Q.V., Sung,\u00a0Y., Li,\u00a0Z., Duerig,\u00a0T., 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In: ICML."},{"key":"10.1016\/j.cviu.2026.104721_b14","doi-asserted-by":"crossref","unstructured":"Khattak,\u00a0M.U., Rasheed,\u00a0H.A., Maaz,\u00a0M., Khan,\u00a0S.H., Khan,\u00a0F.S., 2023a. MaPLe: Multi-modal Prompt Learning. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"10.1016\/j.cviu.2026.104721_b15","doi-asserted-by":"crossref","unstructured":"Khattak,\u00a0M.U., Wasim,\u00a0S.T., Naseer,\u00a0M., Khan,\u00a0S., Yang,\u00a0M., Khan,\u00a0F.S., 2023b. Self-regulating Prompts: Foundational Model Adaptation without Forgetting. In: ICCV.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"10.1016\/j.cviu.2026.104721_b16","series-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017"},{"key":"10.1016\/j.cviu.2026.104721_b17","unstructured":"Kumar,\u00a0A., Raghunathan,\u00a0A., Jones,\u00a0R.M., Ma,\u00a0T., Liang,\u00a0P., 2022. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104721_b18","doi-asserted-by":"crossref","DOI":"10.6028\/jres.124.028","article-title":"A purely algebraic justification of the Kabsch-Umeyama algorithm","author":"Lawrence","year":"2019","journal-title":"J. Res. Natl. Inst. Stand. Technol."},{"key":"10.1016\/j.cviu.2026.104721_b19","doi-asserted-by":"crossref","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.cviu.2026.104721_b20","series-title":"Karlo-v1.0.alpha on COYO-100M and CC15M","author":"Lee","year":"2022"},{"key":"10.1016\/j.cviu.2026.104721_b21","doi-asserted-by":"crossref","unstructured":"Li,\u00a0H., Pan,\u00a0S.J., Wang,\u00a0S., Kot,\u00a0A.C., 2018. Domain Generalization With Adversarial Feature Learning. In: CVPR.","DOI":"10.1109\/CVPR.2018.00566"},{"key":"10.1016\/j.cviu.2026.104721_b22","doi-asserted-by":"crossref","unstructured":"Li,\u00a0D., Yang,\u00a0Y., Song,\u00a0Y., Hospedales,\u00a0T.M., 2017. Deeper, Broader and Artier Domain Generalization. In: ICCV.","DOI":"10.1109\/ICCV.2017.591"},{"key":"10.1016\/j.cviu.2026.104721_b23","unstructured":"Liang,\u00a0W., Zhang,\u00a0Y., Kwon,\u00a0Y., Yeung,\u00a0S., Zou,\u00a0J.Y., 2022. Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning. In: NeurIPS."},{"key":"10.1016\/j.cviu.2026.104721_b24","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0Z., Mao,\u00a0H., Wu,\u00a0C.-Y., Feichtenhofer,\u00a0C., Darrell,\u00a0T., Xie,\u00a0S., 2022. A ConvNet for the 2020s. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.cviu.2026.104721_b25","unstructured":"Loshchilov,\u00a0I., Hutter,\u00a0F., 2019. Decoupled Weight Decay Regularization. In: ICLR."},{"key":"10.1016\/j.cviu.2026.104721_b26","series-title":"Context-aware robust fine-tuning","author":"Mao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104721_b27","doi-asserted-by":"crossref","unstructured":"Marino,\u00a0S., Vandoni,\u00a0J., Aldea,\u00a0E., Lemghari,\u00a0I., H\u00e9garat-Mascle,\u00a0S.L., Jurie,\u00a0F., 2024. ICPR 2024 Competition on Domain Adaptation and GEneralization for Character Classification (DAGECC). In: Pattern Recognition. Competitions - 27th International Conference, ICPR 2024, Kolkata, India, December 1\u20135, 2024, Proceedings, Part XXXIV.","DOI":"10.1007\/978-3-031-80139-6_12"},{"key":"10.1016\/j.cviu.2026.104721_b28","unstructured":"Netzer,\u00a0Y., Wang,\u00a0T., Coates,\u00a0A., Bissacco,\u00a0A., Wu,\u00a0B., Ng,\u00a0A.Y., 2011. Reading Digits in Natural Images with Unsupervised Feature Learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011."},{"key":"10.1016\/j.cviu.2026.104721_b29","series-title":"Domain-unified prompt representations for source-free domain generalization","author":"Niu","year":"2022"},{"key":"10.1016\/j.cviu.2026.104721_b30","doi-asserted-by":"crossref","unstructured":"Peng,\u00a0X., Bai,\u00a0Q., Xia,\u00a0X., Huang,\u00a0Z., Saenko,\u00a0K., Wang,\u00a0B., 2019. Moment Matching for Multi-Source Domain Adaptation. In: ICCV.","DOI":"10.1109\/ICCV.2019.00149"},{"key":"10.1016\/j.cviu.2026.104721_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126658","article-title":"Combined scaling for zero-shot transfer learning","author":"Pham","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.cviu.2026.104721_b32","unstructured":"Radford,\u00a0A., Kim,\u00a0J.W., Hallacy,\u00a0C., Ramesh,\u00a0A., Goh,\u00a0G., Agarwal,\u00a0S., Sastry,\u00a0G., Askell,\u00a0A., Mishkin,\u00a0P., Clark,\u00a0J., Krueger,\u00a0G., Sutskever,\u00a0I., 2021. Learning Transferable Visual Models From Natural Language Supervision. In: ICML."},{"key":"10.1016\/j.cviu.2026.104721_b33","series-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"10.1016\/j.cviu.2026.104721_b34","doi-asserted-by":"crossref","unstructured":"Schubert,\u00a0E., 2021. A Triangle Inequality for Cosine Similarity. In: Similarity Search and Applications - 14th International Conference.","DOI":"10.1007\/978-3-030-89657-7_3"},{"key":"10.1016\/j.cviu.2026.104721_b35","doi-asserted-by":"crossref","unstructured":"Schuhmann,\u00a0C., Beaumont,\u00a0R., Vencu,\u00a0R., Gordon,\u00a0C.W., Wightman,\u00a0R., Cherti,\u00a0M., Coombes,\u00a0T., Katta,\u00a0A., Mullis,\u00a0C., Wortsman,\u00a0M., Schramowski,\u00a0P., Kundurthy,\u00a0S.R., Crowson,\u00a0K., Schmidt,\u00a0L., Kaczmarczyk,\u00a0R., Jitsev,\u00a0J., 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In: Thirty-Sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","DOI":"10.52202\/068431-1833"},{"key":"10.1016\/j.cviu.2026.104721_b36","doi-asserted-by":"crossref","unstructured":"Shermeyer,\u00a0J., Hossler,\u00a0T., Etten,\u00a0A.V., Hogan,\u00a0D., Lewis,\u00a0R., Kim,\u00a0D., 2021. RarePlanes: Synthetic Data Takes Flight. In: IEEE Winter Conference on Applications of Computer Vision. WACV 2021, Waikoloa, HI, USA, January 3\u20138, 2021.","DOI":"10.1109\/WACV48630.2021.00025"},{"key":"10.1016\/j.cviu.2026.104721_b37","series-title":"A closer look at the few-shot adaptation of large vision-language models","author":"Silva-Rodr\u00edguez","year":"2023"},{"key":"10.1016\/j.cviu.2026.104721_b38","doi-asserted-by":"crossref","unstructured":"Sun,\u00a0B., Feng,\u00a0J., Saenko,\u00a0K., 2016. Return of Frustratingly Easy Domain Adaptation. In: AAAI.","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"10.1016\/j.cviu.2026.104721_b39","doi-asserted-by":"crossref","unstructured":"Tan,\u00a0S., Peng,\u00a0X., Saenko,\u00a0K., 2020. Class-Imbalanced Domain Adaptation: An Empirical Odyssey. In: ECCV.","DOI":"10.1007\/978-3-030-66415-2_38"},{"key":"10.1016\/j.cviu.2026.104721_b40","doi-asserted-by":"crossref","unstructured":"Venkateswara,\u00a0H., Eusebio,\u00a0J., Chakraborty,\u00a0S., Panchanathan,\u00a0S., 2017. Deep Hashing Network for Unsupervised Domain Adaptation. In: CVPR.","DOI":"10.1109\/CVPR.2017.572"},{"key":"10.1016\/j.cviu.2026.104721_b41","doi-asserted-by":"crossref","unstructured":"Vidit,\u00a0V., Engilberge,\u00a0M., Salzmann,\u00a0M., 2023. CLIP the Gap: A Single Domain Generalization Approach for Object Detection. In: CVPR.","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"10.1016\/j.cviu.2026.104721_b42","series-title":"The caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.cviu.2026.104721_b43","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0S., Chen,\u00a0X., Wang,\u00a0Y., Long,\u00a0M., Wang,\u00a0J., 2020. Progressive Adversarial Networks for Fine-Grained Domain Adaptation. In: CVPR.","DOI":"10.1109\/CVPR42600.2020.00923"},{"key":"10.1016\/j.cviu.2026.104721_b44","series-title":"Learning to diversify for single domain generalization","author":"Wang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104721_b45","series-title":"LanDA: Language-guided multi-source domain adaptation","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104721_b46","doi-asserted-by":"crossref","unstructured":"Wortsman,\u00a0M., Ilharco,\u00a0G., Kim,\u00a0J.W., Li,\u00a0M., Kornblith,\u00a0S., Roelofs,\u00a0R., Lopes,\u00a0R.G., Hajishirzi,\u00a0H., Farhadi,\u00a0A., Namkoong,\u00a0H., Schmidt,\u00a0L., 2022. Robust fine-tuning of zero-shot models. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"10.1016\/j.cviu.2026.104721_b47","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0M., Zhang,\u00a0J., Ni,\u00a0B., Li,\u00a0T., Wang,\u00a0C., Tian,\u00a0Q., Zhang,\u00a0W., 2020. Adversarial Domain Adaptation with Domain Mixup. In: AAAI.","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"10.1016\/j.cviu.2026.104721_b48","series-title":"Generalizing CLIP to unseen domain via text-guided diverse novel feature synthesis","author":"Yan","year":"2024"},{"key":"10.1016\/j.cviu.2026.104721_b49","doi-asserted-by":"crossref","unstructured":"Zhou,\u00a0K., Yang,\u00a0J., Loy,\u00a0C.C., Liu,\u00a0Z., 2022a. Conditional Prompt Learning for Vision-Language Models. In: CVPR.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.cviu.2026.104721_b50","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","author":"Zhou","year":"2022","journal-title":"IJCV"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000883?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000883?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T22:14:57Z","timestamp":1776204897000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":50,"alternative-id":["S1077314226000883"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104721","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Text-Aided Domain Adaptation for CLIP-like models and application to challenging domain shifts","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104721","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104721"}}