{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:17:56Z","timestamp":1778782676239,"version":"3.51.4"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2025JJ70455"],"award-info":[{"award-number":["2025JJ70455"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372167"],"award-info":[{"award-number":["62372167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.eswa.2026.131248","type":"journal-article","created":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:11:38Z","timestamp":1768705898000},"page":"131248","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ImCapDA: Fine-tuning CLIP via image captions for unsupervised domain adaptation"],"prefix":"10.1016","volume":"309","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7341-1655","authenticated-orcid":false,"given":"Weiwei","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0625-0804","authenticated-orcid":false,"given":"Guangyi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6573-4617","authenticated-orcid":false,"given":"Shun","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5902-1824","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0928-6848","authenticated-orcid":false,"given":"Liming","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1765-7741","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131248_bib0001","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"729","article-title":"Prompt-based distribution alignment for unsupervised domain adaptation","volume":"vol. 38","author":"Bai","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7181","article-title":"Reusing the task-specific classifier as a discriminator: Discriminator-free adversarial domain adaptation","author":"Chen","year":"2022"},{"key":"10.1016\/j.eswa.2026.131248_bib0003","unstructured":"Chen, S., Zhang, Y., Jiang, W., Lu, J., & Zhang, Y. (2024). Vllavo: Mitigating visual gap through llms. arXiv preprint arXiv: 2401.03253."},{"key":"10.1016\/j.eswa.2026.131248_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23595","article-title":"Disentangled prompt representation for domain generalization","author":"Cheng","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0005","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23375","article-title":"Domain-agnostic mutual prompting for unsupervised domain adaptation","author":"Du","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13350","article-title":"Ad-clip: Adapting domains in prompt space using clip","author":"Ge","year":"2022"},{"key":"10.1016\/j.eswa.2026.131248_bib0007","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"2994","article-title":"Reclip: Refine contrastive language image pre-training with source free domain adaptation","author":"Hu","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0008","unstructured":"Huang, T., Chu, J., & Wei, F. (2022). Unsupervised prompt learning for vision-language models. arXiv preprint arXiv: 2204.03649."},{"key":"10.1016\/j.eswa.2026.131248_bib0009","series-title":"Nips","first-page":"2672","article-title":"Generative adversarial nets","author":"IJ","year":"2014"},{"key":"10.1016\/j.eswa.2026.131248_bib0010","series-title":"International conference on machine learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.eswa.2026.131248_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","article-title":"Contrastive adaptation network for unsupervised domain adaptation","author":"Kang","year":"2019"},{"key":"10.1016\/j.eswa.2026.131248_bib0012","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"2691","article-title":"Empowering unsupervised domain adaptation with large-scale pre-trained vision-language models","author":"Lai","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0013","series-title":"Proceedings of the ieee\/cvf winter conference on applications of computer vision","first-page":"2691","article-title":"Empowering unsupervised domain adaptation with large-scale pre-trained vision-language models","author":"Lai","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0014","series-title":"International conference on machine learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.131248_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23364","article-title":"Split to merge: Unifying separated modalities for unsupervised domain adaptation","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0016","series-title":"International conference on machine learning","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","author":"Liang","year":"2020"},{"key":"10.1016\/j.eswa.2026.131248_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16632","article-title":"Domain adaptation with auxiliary target domain-oriented classifier","author":"Liang","year":"2021"},{"key":"10.1016\/j.eswa.2026.131248_bib0018","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"1173","article-title":"Padclip: Pseudo-labeling with adaptive debiasing in clip for unsupervised domain adaptation","author":"Lin","year":"2023"},{"key":"10.1016\/j.eswa.2026.131248_bib0019","series-title":"Advances in neural information processing systems","first-page":"1640","article-title":"Conditional adversarial domain adaptation","author":"Long","year":"2018"},{"key":"10.1016\/j.eswa.2026.131248_bib0020","unstructured":"Long, S., Wang, L., Zhao, Z., Tan, Z., Wu, Y., Wang, S., & Wang, J. (2024). Training-free unsupervised prompt for vision-language models. arXiv preprint arXiv: 2404.16339."},{"key":"10.1016\/j.eswa.2026.131248_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2239","article-title":"Transferrable prototypical networks for unsupervised domain adaptation","author":"Pan","year":"2019"},{"key":"10.1016\/j.eswa.2026.131248_bib0022","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"15691","article-title":"What does a platypus look like? generating customized prompts for zero-shot image classification","author":"Pratt","year":"2023"},{"key":"10.1016\/j.eswa.2026.131248_bib0023","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.131248_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125543","article-title":"H3t: Hierarchical transferable transformer with tokenmix for unsupervised domain adaptation","volume":"262","author":"Ren","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131248_bib0025","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"18928","article-title":"Domain-specificity inducing transformers for source-free domain adaptation","author":"Sanyal","year":"2023"},{"key":"10.1016\/j.eswa.2026.131248_bib0026","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131248_bib0027","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23711","article-title":"Source-free domain adaptation with frozen multimodal foundation model","author":"Tang","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0028","unstructured":"Tanwisuth, K., Zhang, S., Zheng, H., He, P., & Zhou, M. (2023a). Pouf: Prompt-oriented unsupervised fine-tuning for large pre-trained models. arXiv preprint arXiv: 2305.00350."},{"key":"10.1016\/j.eswa.2026.131248_bib0029","series-title":"International conference on machine learning","first-page":"33816","article-title":"Pouf: Prompt-oriented unsupervised fine-tuning for large pre-trained models","author":"Tanwisuth","year":"2023"},{"key":"10.1016\/j.eswa.2026.131248_bib0030","unstructured":"Teterwak, P., Saito, K., Tsiligkaridis, T., Plummer, B. A., & Saenko, K. (2025). Is large-scale pretraining the secret to good domain generalization?Proceedings of international conference on learning representations."},{"key":"10.1016\/j.eswa.2026.131248_bib0031","series-title":"Proceedings of the computer vision and pattern recognition conference","article-title":"Preserving clusters in prompt learning for unsupervised domain adaptation","author":"Vuong","year":"2025"},{"key":"10.1016\/j.eswa.2026.131248_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7151","article-title":"Exploring domain-invariant parameters for source free domain adaptation","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131248_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5749","article-title":"Learning hierarchical prompt with structured linguistic knowledge for vision-language models","volume":"vol. 38","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.131248_bib0034","unstructured":"Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021). Finetuned language models are zero-shot learners. arXiv preprint arXiv: 2109.01652."},{"key":"10.1016\/j.eswa.2026.131248_bib0035","series-title":"2025\u202fIEEE\/CVF Winter conference on applications of computer vision(WACV)","first-page":"6528","article-title":"Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance","author":"Westf","year":"2025"},{"key":"10.1016\/j.eswa.2026.131248_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110533","article-title":"Unified multi-level neighbor clustering for source-free unsupervised domain adaptation","volume":"153","author":"Xiao","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.131248_bib0037","series-title":"Spa: A graph spectral alignment perspective for domain adaptation","author":"Xiao","year":"2023"},{"key":"10.1016\/j.eswa.2026.131248_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126744","article-title":"Unsupervised domain adaptation via optimal prototypes transport","volume":"272","author":"Xu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131248_bib0039","doi-asserted-by":"crossref","unstructured":"Xue, L., Shu, M., Awadalla, A., Wang, J., Yan, A., Purushwalkam, S., Zhou, H., Prabhu, V., Dai, Y., Ryoo, M. S., Kendre, S., Zhang, J., Qin, C., Zhang, S., Chen, C.-C., Yu, N., Tan, J., Awalgaonkar, T. M., Heinecke, S., Wang, H., Choi, Y., Schmidt, L., Chen, Z., Savarese, S., Niebles, J. C., Xiong, C., & Xu, R. (2024). xgen-MM (BLIP-3): A family of open large multimodal models. https:\/\/arxiv.org\/abs\/2408.08872.","DOI":"10.1109\/ICCVW69036.2025.00644"},{"key":"10.1016\/j.eswa.2026.131248_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13353","article-title":"Tvt: Transferable vision transformer for unsupervised domain adaptation","author":"Yang","year":"2021"},{"key":"10.1016\/j.eswa.2026.131248_bib0041","unstructured":"Zhang, S., Gong, C., & Choi, E. (2021). Capturing label distribution: A case study in nli. arXiv preprint arXiv: 2102.06859."},{"key":"10.1016\/j.eswa.2026.131248_bib0042","series-title":"International conference on machine learning","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","author":"Zhang","year":"2019"},{"key":"10.1016\/j.eswa.2026.131248_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16601","article-title":"Domain adaptation via prompt learning","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131248_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127090","article-title":"Dual-level redundancy elimination for unsupervised domain adaptation","volume":"276","author":"Zhao","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131248_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125602","article-title":"Deep joint subdomain alignment for unsupervised domain adaptation","volume":"262","author":"Zhong","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"9","key":"10.1016\/j.eswa.2026.131248_bib0046","doi-asserted-by":"crossref","first-page":"8201","DOI":"10.1109\/TCSVT.2024.3391304","article-title":"Unsupervised domain adaption harnessing vision-language pre-training","volume":"34","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426001624?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426001624?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:46:50Z","timestamp":1778780810000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426001624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":46,"alternative-id":["S0957417426001624"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131248","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ImCapDA: Fine-tuning CLIP via image captions for unsupervised domain adaptation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131248","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"131248"}}