{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:22:43Z","timestamp":1790727763987,"version":"4.1.0"},"reference-count":341,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"ETH Mobility Initiative","award":["SENTINEL"],"award-info":[{"award-number":["SENTINEL"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276256, U2441251"],"award-info":[{"award-number":["62276256, U2441251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11263-026-02987-w","type":"journal-article","created":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T11:12:13Z","timestamp":1786187533000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adapting Vision-Language Models Without Labels: A Comprehensive Survey"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8562-1946","authenticated-orcid":false,"given":"Hao","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3890-1894","authenticated-orcid":false,"given":"Jian","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eleni","family":"Chatzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Fink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"2987_CR1","unstructured":"Abdelhamed, A., Afifi, M., & Go, A. (2024). What do you see? Enhancing zero-shot image classification with multimodal large language models. Preprint at arXiv:2405.15668"},{"key":"2987_CR2","doi-asserted-by":"crossref","unstructured":"Adachi, K., Shin\u2019ya, Y., & Hamagami, T. (2025). Uniformity first: Uniformity-aware test-time adaptation of vision-language models against image corruption arXiv:2505.12912 arXiv preprint.","DOI":"10.2139\/ssrn.5676708"},{"key":"2987_CR3","doi-asserted-by":"crossref","unstructured":"Agrawal, H., Desai, K., Wang, Y., Chen, X., Jain, R., Johnson, M., Batra, D., Parikh, D., Lee, S., & Anderson., P. (2019). Nocaps: Novel object captioning at scale. In ICCV.","DOI":"10.1109\/ICCV.2019.00904"},{"key":"2987_CR4","doi-asserted-by":"crossref","unstructured":"Ali, E., Silva, S., & Khan, M.H. (2025). Dpa: Dual prototypes alignment for unsupervised adaptation of vision-language models. In WACV.","DOI":"10.1109\/WACV61041.2025.00593"},{"key":"2987_CR5","unstructured":"Ali, E., Arora, C., & Khan, M. H. (2025). Prototype-guided pseudo-labeling with neighborhood-aware consistency for unsupervised adaptation arXiv:2507.22075 arXiv preprint."},{"key":"2987_CR6","unstructured":"Ali, E., & Khan, M. H. (2023). Noise-tolerant few-shot unsupervised adapter for vision-language models. BMVC"},{"key":"2987_CR7","doi-asserted-by":"crossref","unstructured":"Ali, E., Silva, S., Arora, C., & Khan, M. H. (2025). Towards fine-grained adaptation of clip via a self-trained alignment score arXiv:2507.09615 arXiv preprint.","DOI":"10.1109\/WACV61042.2026.00569"},{"key":"2987_CR8","unstructured":"An, B., Zhu, S., & Panaitescu-Liess, M.-A., Mummadi, C.K., & Huang, F. (2023). Perceptionclip: Visual classification by inferring and conditioning on contexts. In ICLR."},{"key":"2987_CR9","doi-asserted-by":"crossref","unstructured":"Bao, W., Wei, T., Wang, H., & He, J. (2023). Adaptive test-time personalization for federated learning. In NeurIPS.","DOI":"10.52202\/075280-3403"},{"key":"2987_CR10","doi-asserted-by":"crossref","unstructured":"Bao, W., Deng, R., & He, J. (2025). Mint: A simple test-time adaptation of vision-language models against common corruptions arXiv:2510.22127 arXiv preprint.","DOI":"10.52202\/085713-1964"},{"key":"2987_CR11","doi-asserted-by":"crossref","unstructured":"Belal, A., Medeiros, H.R., Pedersoli, M., & Granger, E. (2025). Vlod-tta: Test-time adaptation of vision-language object detectors. arXiv preprint arXiv:2510.00458.","DOI":"10.1109\/ICCV51701.2025.00210"},{"key":"2987_CR12","doi-asserted-by":"crossref","unstructured":"Benigmim, Y., Fahes, M., Tuan-Hung, V., Bursuc, A., & Charette, R.d., (2025). Floss: Free lunch in open-vocabulary semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV51701.2025.01994"},{"key":"2987_CR13","unstructured":"B\u00e9ria Chingnab\u00e9 Kalp\u00e9lb\u00e9, A., Gabriel Adaambiik, W., & Peng. (2025). Vision language models in medicine arXiv:2503.01863 arXiv preprint."},{"key":"2987_CR14","doi-asserted-by":"crossref","unstructured":"Bosetti, M., Zhang, S., Liberatori, B., Zara, G., Ricci, E., & Rota, P. (2024). Text-enhanced zero-shot action recognition: A training-free approach. In ICPR.","DOI":"10.1007\/978-3-031-78354-8_21"},{"key":"2987_CR15","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van Gool, L. (2014). Food-101-mining discriminative components with random forests. ECCV","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2987_CR16","doi-asserted-by":"crossref","unstructured":"Bousselham, W., Petersen, F., Ferrari, V. & Kuehne., H. (2024). Grounding everything: Emerging localization properties in vision-language transformers. In CVPR.","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"2987_CR17","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., & Agarwal, S. (2020). Language models are few-shot learners. In NeurIPS."},{"key":"2987_CR18","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., & Niebles, J.C. (2015). Activitynet: A large-scale video benchmark for human activity understanding. In CVPR.","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2987_CR19","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., & Ferrari, V., (2018). Coco-stuff: Thing and stuff classes in context. In CVPR.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"2987_CR20","unstructured":"Cai, L., Kang, J., Li, S., Ma, W., Xie, B., Qin, Z., & Liang., J. (2025). From local details to global context: Advancing vision-language models with attention-based selection. In ICML."},{"key":"2987_CR21","doi-asserted-by":"crossref","unstructured":"Cao, A.-Q., Jaritz, M., Guillaumin, M., & de Charette, R., & Bazzani., L. (2025). Latteclip: Unsupervised clip fine-tuning via LMM-synthetic texts. In WACV.","DOI":"10.1109\/WACV61041.2025.00492"},{"key":"2987_CR22","unstructured":"Cao, T.H., Tran, T.K., Pham, G.T., Diep, T.N., & Nguyen, T.B. (2025). LGCA: Enhancing semantic representation via progressive expansion. arXiv preprint arXiv:2511.00419."},{"key":"2987_CR23","unstructured":"Cao, C., Zhong, Z., Zhou, Z., Liu, Y., Liu, T., & Han, B. (2024). Envisioning outlier exposure by large language models for out-of-distribution detection. In ICML."},{"key":"2987_CR24","unstructured":"Cao, C., Zhong, Z., Zhou, Z., Liu, T., Liu, Y., Zhang, K., & Han, B. (2025). Noisy test-time adaptation in vision-language models. In ICLR."},{"key":"2987_CR25","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2987_CR26","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., & Zisserman, A. (2018). A short note about kinetics-600 arXiv:1808.01340 arXiv preprint."},{"key":"2987_CR27","doi-asserted-by":"crossref","unstructured":"Chao, W.-L., Changpinyo, S., Gong, B., & Sha, F. (2016). An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. ECCV","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"2987_CR28","unstructured":"Chen, X., Huang, J., Jiang, Q., Huang, F., Fu, X., Jiang, J., & Wang, Z. (2025). Small aid, big leap: Efficient test-time adaptation for vision-language models with adaptnet. arXiv preprint arXiv:2506.02671."},{"key":"2987_CR29","doi-asserted-by":"crossref","unstructured":"Chen, R., Liu, Y., Kong, L., Zhu, X., Ma, Y., Li, Y., Hou, Y., Qiao, Y., & Wang, W. (2023). Clip2scene: Towards label-efficient 3d scene understanding by clip. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"2987_CR30","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z., & Gu, L. (2024). Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271."},{"key":"2987_CR31","doi-asserted-by":"crossref","unstructured":"Chen, H., Xu, Y., Xu, Y., Zhang, Y., & Cui, L. (2024). Test-time medical image segmentation using clip-guided sam adaptation. In BIBM.","DOI":"10.1109\/BIBM62325.2024.10822570"},{"key":"2987_CR32","unstructured":"Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., & Zitnick, C. L. (2015). Microsoft coco captions: Data collection and evaluation server arXiv:1504.00325 arXiv preprint."},{"key":"2987_CR33","doi-asserted-by":"crossref","unstructured":"Chen, D., Wang, D., Darrell, T., & Ebrahimi, S. (2022). Contrastive test-time adaptation. CVPR","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"2987_CR34","doi-asserted-by":"crossref","unstructured":"Christoph, H., Lampert, H., Nickisch, S., & Harmeling. (2009). Learning to detect unseen object classes by between-class attribute transfer. CVPR","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"2987_CR35","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., Rezende, R.S.D., Kalantidis, Y., & Larlus., Diane. (2021). In CVPR: Probabilistic embeddings for cross-modal retrieval.","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"2987_CR36","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos., I., Mohamed., S., & Vedaldi., A., (2014). Describing textures in the wild. CVPR","DOI":"10.1109\/CVPR.2014.461"},{"key":"2987_CR37","doi-asserted-by":"crossref","unstructured":"Codella, N. C. F., David Gutman, M., Celebi, E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., Skin lesion analysis toward melanoma detection: A challenge at the, et al. (2017). International Symposium on Biomedical Imaging (ISBI), hosted by the International Skin Imaging Collaboration (ISIC). In ISB,I, 2018.","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"2987_CR38","doi-asserted-by":"crossref","unstructured":"Conti, A., Fini, E., Mancini, M., Rota, P., Wang, Y., & Ricci, E. (2024). Vocabulary-free image classification and semantic segmentation. arXiv preprint arXiv:2404.10864.","DOI":"10.52202\/075280-1337"},{"key":"2987_CR39","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"2987_CR40","unstructured":"Cui, S., Xu, J., Li, Y., Tang, X., Li, J., Zhou, J., Xu, F., Sun, F., & Xiong, H. (2025). Bayestta: Continual-temporal test-time adaptation for vision-language models via gaussian discriminant analysis. arXiv preprint arXiv:2507.08607."},{"key":"2987_CR41","doi-asserted-by":"crossref","unstructured":"d Nguyen, A.T., Tai, K.S., Chen, B-C., Shukla, S.N., Yu, H., Torr, P., Tian, T.-P., & Lim, S-N. (2024). UCAP: An unsupervised prompting method for vision-language models. In ECCV.","DOI":"10.1007\/978-3-031-72904-1_25"},{"key":"2987_CR42","doi-asserted-by":"crossref","unstructured":"Dai, Q., & Yang, S. (2025). Free on the fly: Enhancing flexibility in test-time adaptation with online em. CVPR","DOI":"10.1109\/CVPR52734.2025.00891"},{"key":"2987_CR43","unstructured":"Dastmalchi, H., An, A., Cheraghian, A. (2025). Etta: Efficient test-time adaptation for vision-language models through dynamic embedding updates. arXiv preprint arXiv:2508.05898."},{"key":"2987_CR44","doi-asserted-by":"crossref","unstructured":"Deng, Z., Chen, Z., Niu, S., Li, T., Zhuang, B., & Tan, M. (2023). Efficient test-time adaptation for super-resolution with second-order degradation and reconstruction. In NeurIPS.","DOI":"10.52202\/075280-3264"},{"key":"2987_CR45","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei., L. (2009). Imagenet: A large-scale hierarchical image database. In CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2987_CR46","unstructured":"Deng, R., Bao, W., Wei, T., & He, J. (2025). Panda: Test-time adaptation with negative data augmentation arXiv:2511.10481 arXiv preprint."},{"key":"2987_CR47","unstructured":"Ding, Z., Ding, C., Shao, Z., & Tao, D. (2021). Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666."},{"key":"2987_CR48","unstructured":"Ding, C., Gao, X., Dong, S., He, Y., Wang, Q., Song, X., Kot, A., & Gong, Y. (2025). Space rotation with basis transformation for training-free test-time adaptation arXiv:2502.19946 arXiv preprint."},{"key":"2987_CR49","doi-asserted-by":"crossref","unstructured":"Dong, H., Chen, X., Dusmanu, M., Larsson, V., Pollefeys, M., & Stachniss, C. (2023). Learning-based dimensionality reduction for computing compact and effective local feature descriptors. In ICRA.","DOI":"10.1109\/ICRA48891.2023.10161381"},{"key":"2987_CR50","doi-asserted-by":"crossref","unstructured":"Dong, H., Zhao, Y., Chatzi, E., Fink, O. (2024). Multiood: Scaling out-of-distribution detection for multiple modalities. In NeurIPS.","DOI":"10.52202\/079017-4106"},{"key":"2987_CR51","unstructured":"Dong, H., Chatzi, E., & Fink, O. (2025). Towards robust multimodal open-set test-time adaptation via adaptive entropy-aware optimization. ICLR"},{"key":"2987_CR52","unstructured":"Dong, H., Liu, M., Liang, J., Chatzi, E., & Fink, O. (2025). To trust or not to trust your vision-language model\u2019s prediction arXiv:2505.23745 arXiv preprint."},{"key":"2987_CR53","doi-asserted-by":"crossref","unstructured":"Dong, H., Liu, M., Zhou, K., Chatzi, E., Kannala, J., Stachniss, C., & Fink, O. (2025). Advances in multimodal adaptation and generalization: From traditional approaches to foundation models arXiv:2501.18592 arXiv preprint.","DOI":"10.1109\/TPAMI.2026.3651319"},{"key":"2987_CR54","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., & Uszkoreit, J. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR."},{"key":"2987_CR55","unstructured":"Eom, S., Ho, N., Oh, J., & Yun, S.-Y. (2023). Cross-modal retrieval meets inference: Improving zero-shot classification with cross-modal retrieval arXiv:2308.15273 arXiv preprint."},{"key":"2987_CR56","unstructured":"Esfandiarpoor, R., Stephen, H., & Bach. (2023). Follow-up differential descriptions: Language models resolve ambiguities for image classification. ICLR"},{"key":"2987_CR57","doi-asserted-by":"crossref","unstructured":"Everingham, M., Eslami, S.A., Van\u00a0Gool, L., Williams, C.K., Winn, J., & Zisserman, A., (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111:98\u2013136.","DOI":"10.1007\/s11263-014-0733-5"},{"key":"2987_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106230","volume":"174","author":"Y Fang","year":"2024","unstructured":"Fang, Y., Yap, P.-T., Lin, W., Zhu, H., & Liu, M. (2024). Source-free unsupervised domain adaptation: A survey. Neural Networks, 174, Article 106230.","journal-title":"Neural Networks"},{"key":"2987_CR59","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009). Describing objects by their attributes. CVPR","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"2987_CR60","doi-asserted-by":"crossref","unstructured":"Farina, M., Franchi, G., Iacca, G., Mancini, M., & Ricci, E. (2024). Frustratingly easy test-time adaptation of vision-language models. In NeurIPS.","DOI":"10.52202\/079017-4099"},{"key":"2987_CR61","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. CVPR Workshops"},{"key":"2987_CR62","doi-asserted-by":"crossref","unstructured":"Felix, R., Reid, I., & Carneiro, G. (2018). Multi-modal cycle-consistent generalized zero-shot learning. In ECCV,","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"2987_CR63","doi-asserted-by":"crossref","unstructured":"Feng, C.-M., He, Y., Zou, J., Khan, S., Xiong, H., Li, Z., Zuo, W., Goh, R.S.M., & Liu, Y. (2025). Diffusion-enhanced test-time adaptation with text and image augmentation. International Journal of Computer Vision, 1\u201316.","DOI":"10.1007\/s11263-025-02412-8"},{"key":"2987_CR64","doi-asserted-by":"crossref","unstructured":"Feng, C.-M., Yu, K., Liu, Y., Khan, S., & Zuo, W. (2023). Diverse data augmentation with diffusions for effective test-time prompt tuning. ICCV","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"2987_CR65","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Ranzato, M., & Mikolov, T. (2013). Devise: A deep visual-semantic embedding model. In NeurIPS."},{"key":"2987_CR66","doi-asserted-by":"crossref","unstructured":"Fuchs, C., Zanella, M., & Vleeschouwer, C. D. (2025). Online gaussian test-time adaptation of vision-language models arXiv:2501.04352 arXiv preprint.","DOI":"10.1109\/CVPRW67362.2025.00018"},{"issue":"2","key":"2987_CR67","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Yu. (2024). Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision, 132(2), 581\u2013595.","journal-title":"International Journal of Computer Vision"},{"key":"2987_CR68","doi-asserted-by":"crossref","unstructured":"Ge, Y., Ren, J., Gallagher, A., Wang, Y., Yang, M.-H., Adam, H., Itti, L., Lakshminarayanan, B., & Zhao, J. (2023). Improving zero-shot generalization and robustness of multi-modal models. CVPR","DOI":"10.1109\/CVPR52729.2023.01067"},{"key":"2987_CR69","doi-asserted-by":"crossref","unstructured":"Gong, T., Kim, Y., Lee, T., & Chottananurak, S., & Lee, S.-J. (2023). Sotta: Robust test-time adaptation on noisy data streams. In NeurIPS.","DOI":"10.52202\/075280-0620"},{"key":"2987_CR70","doi-asserted-by":"crossref","unstructured":"Gou, J., Yu, B., Stephen, J., Maybank, D., & Tao. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6), 1789\u20131819.","DOI":"10.1007\/s11263-021-01453-z"},{"key":"2987_CR71","doi-asserted-by":"crossref","unstructured":"Guan, Z., Yucan, Z., Liu, W., Gu, X. (2025). Statistics caching test-time adaptation for vision-language models. In NeurIPS.","DOI":"10.52202\/085713-0230"},{"key":"2987_CR72","unstructured":"Gu, J., Han, Z., Chen, S., Beirami, A., He, B., Zhang, G., Liao, R., Qin, Y., Volker Tresp, P., & Torr. (2023). A systematic survey of prompt engineering on vision-language foundation models arXiv:2307.12980 arXiv preprint."},{"issue":"12","key":"2987_CR73","doi-asserted-by":"publisher","first-page":"9052","DOI":"10.1109\/TPAMI.2024.3415112","volume":"46","author":"J Gui","year":"2024","unstructured":"Gui, J., Chen, T., Zhang, J., Cao, Q., Sun, Z., Luo, H., & Tao, D. (2024). A survey on self-supervised learning: Algorithms, applications, and future trends. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9052\u20139071.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2987_CR74","doi-asserted-by":"crossref","unstructured":"Guo, Z., Dong, B., Ji, Z., Bai, J., Guo, Y., & Zuo, W. (2023). Texts as images in prompt tuning for multi-label image recognition. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"2987_CR75","doi-asserted-by":"crossref","unstructured":"Guo, Z., Dong, B., Ji, Z., Bai, J., Guo, Y., & Zuo, W. (2023). Texts as images in prompt tuning for multi-label image recognition. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"2987_CR76","doi-asserted-by":"crossref","unstructured":"Guo, K., Sheng, L., Yu, Y., Liang, J., Wang, Z., & He, R. (2025). Cooperative pseudo labeling for unsupervised federated classification. In ICCV.","DOI":"10.1109\/ICCV51701.2025.00318"},{"key":"2987_CR77","doi-asserted-by":"crossref","unstructured":"Guo, Z., Zhang, R., Qiu, L., Ma, X., Miao, X., He, X. & Cui, B. (2023). Calip: Zero-shot enhancement of clip with parameter-free attention. In AAAI.","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"2987_CR78","doi-asserted-by":"crossref","unstructured":"Hajimiri, S., Ayed, I. B., & Dolz, J. (2025). Pay attention to your neighbours: Training-free open-vocabulary semantic segmentation. In WACV.","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"2987_CR79","unstructured":"Hakim, G. A. V., Osowiechi, D., Noori, M., Cheraghalikhani, M., Bahri, A., Yazdanpanah, M., Ayed, I.B., & Desrosiers, C. (2024). Clipartt: Adaptation of clip to new domains at test time. In WACV."},{"key":"2987_CR80","unstructured":"Han, J., & Hwang, W. (2025). D-TPT: Dimensional entropy maximization for calibrating test-time prompt tuning in vision-language models. arXiv preprint arXiv:2510.09473."},{"key":"2987_CR81","doi-asserted-by":"crossref","unstructured":"Han, Z., Yang, J., Li, J., Hu, Q., Xu, Q., Shou, M.Z., & Zhang, C. (2024). Dota: Distributional test-time adaptation of vision-language models. arXiv preprint arXiv:2409.19375.","DOI":"10.52202\/085713-4779"},{"key":"2987_CR82","doi-asserted-by":"crossref","unstructured":"Han, H., Wang, A. J., & Liu, F. (2025). Negation-aware test-time adaptation for vision-language models arXiv:2507.19064 arXiv preprint.","DOI":"10.1109\/TPAMI.2026.3703017"},{"issue":"7","key":"2987_CR83","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019). Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7), 2217\u20132226.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2987_CR84","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., & Song, D. (2019). Using self-supervised learning can improve model robustness and uncertainty. In NeurIPS."},{"key":"2987_CR85","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart., S., Steinhardt., J., & Song., D., (2021). Natural adversarial examples. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"2987_CR86","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., & Guo, M. (2021). The many faces of robustness: A critical analysis of out-of-distribution generalization. ICCV","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"2987_CR87","unstructured":"Hendrycks, D., & Dietterich, T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. ICLR"},{"key":"2987_CR88","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le Bras, R., & Choi., Y. (2021). Clipscore: A reference-free evaluation metric for image captioning. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"2987_CR89","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, Y., & Wang, Z. (2025). Progressive distribution bridging: Unsupervised adaptation for large-scale pre-trained models via adaptive auxiliary data. ICCV","DOI":"10.1109\/ICCV51701.2025.00314"},{"key":"2987_CR90","unstructured":"Hu, X., Zhang, K., Sun, M., Chen, A., Kuo, C.-H., & Nevatia, R. (2024). Bafta: Backprop-free test-time adaptation for zero-shot vision-language models. arXiv preprint arXiv:2406.11309."},{"key":"2987_CR91","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhang, K., Xia, L., Chen, A., Luo, J., Sun, Y., Wang, K., Qiao, N., Zeng, X., Sun, M., & Kuo, C.H., (2024). Reclip: Refine contrastive language image pre-training with source free domain adaptation. In WACV.","DOI":"10.1109\/WACV57701.2024.00297"},{"key":"2987_CR92","unstructured":"Huang, J., Guan, D., Xiao, A., & Lu, S. (2021). Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data. In NeurIPS."},{"key":"2987_CR93","doi-asserted-by":"crossref","unstructured":"Huang, F., Jiang, J., Jiang, Q., Li, H., Khan, F.N., & Wang, Z. (2025). Cosmic: Clique-oriented semantic multi-space integration for robust clip test-time adaptation. In CVPR.","DOI":"10.1109\/CVPR52734.2025.00913"},{"key":"2987_CR94","unstructured":"Huang, J., Zhang, J., Qiu, H., Jin, S., & Lu, S. (2023). Prompt ensemble self-training for open-vocabulary domain adaptation. arXiv preprint arXiv:2306.16658."},{"key":"2987_CR95","unstructured":"Huang, T., Chu, J., & Wei, F. (2022). Unsupervised prompt learning for vision-language models arXiv:2204.03649 arXiv preprint."},{"key":"2987_CR96","doi-asserted-by":"crossref","unstructured":"Idrees, H., Zamir, A.R., Jiang, Y-G., Gorban, A., Laptev, I., Sukthankar, R., & Shah, M. (2017). The thumos challenge on action recognition for videos \u201cin the wild\u201d. Computer Vision and Image Understanding, 155:1\u201323.","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"2987_CR97","unstructured":"Imam, M.F., Marew, R.F., Hassan, J., Fiaz, M., Aji, AF., Cholakkal, H. (2024). Clip meets Dino for tuning zero-shot classifier using unlabeled image collections. arXiv preprint arXiv:2411.19346."},{"key":"2987_CR98","doi-asserted-by":"crossref","unstructured":"Imam, R., Gani, H., Huzaifa, M., & Nandakumar, K. (2024). Test-time low rank adaptation via confidence maximization for zero-shot generalization of vision-language models. WACV","DOI":"10.1109\/WACV61041.2025.00532"},{"key":"2987_CR99","doi-asserted-by":"crossref","unstructured":"Imam, R., Hanif, A., & Zhang, J. (2025). Khaled Waleed Dawoud, Yova Kementchedjhieva, and Mohammad Yaqub. Noise is an efficient learner for zero-shot vision-language models arXiv:2502.06019 arXiv preprint.","DOI":"10.1109\/ICCVW69036.2025.00613"},{"key":"2987_CR100","doi-asserted-by":"crossref","unstructured":"Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019). Label propagation for deep semi-supervised learning. CVPR","DOI":"10.1109\/CVPR.2019.00521"},{"key":"2987_CR101","unstructured":"Jaeger, S., Candemir, S., Antani, S., Y\u00ec-Xi\u00e1ng, J., W\u00e1ng, P.-X., Lu, G., & Thoma. (2014). Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quantitative Imaging in Medicine and Surgery, 4(6), 475."},{"key":"2987_CR102","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac, J., Donahue, P., Luc, A., Miech, I., Barr, Y., Hasson, K., Lenc, A., Mensch, K., Millican, M., & Reynolds. (2022). Flamingo: A visual language model for few-shot learning. NeurIPS","DOI":"10.52202\/068431-1723"},{"key":"2987_CR103","doi-asserted-by":"crossref","unstructured":"Jiang, H., Ma, X., Nie, W., Zhiding, Yu., Zhu, Y., & Anandkumar., A. (2022). Bongard-hoi: Benchmarking few-shot visual reasoning for human-object interactions. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01847"},{"key":"2987_CR104","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q., Sung, Y.-H., Li, Z., & Duerig, T. (2021). Scaling up visual and vision-language representation learning with noisy text supervision. ICML"},{"key":"2987_CR105","unstructured":"Kahana, J., Cohen, N., & Hoshen, Y. (2022). Improving zero-shot models with label distribution priors. arXiv preprint arXiv:2212.00784."},{"key":"2987_CR106","unstructured":"Kalantidis, Y., & Tolias, G. (2024). Label propagation for zero-shot classification with vision-language models. CVPR"},{"key":"2987_CR107","doi-asserted-by":"crossref","unstructured":"Kang, D., & Cho, M. (2024). In defense of lazy visual grounding for open-vocabulary semantic segmentation. ECCV","DOI":"10.1007\/978-3-031-72940-9_9"},{"key":"2987_CR108","doi-asserted-by":"crossref","unstructured":"Karmanov, A., Guan, D., Lu, S., El Saddik, A., & Xing, E. (2024). Efficient test-time adaptation of vision-language models. CVPR","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"2987_CR109","doi-asserted-by":"crossref","unstructured":"Kermany, D.S., Goldbaum, M., Cai, W., Valentim, C.CS., Liang, H., Baxter, S.L., McKeown, A., Yang, G., Wu, X., Yan, F., & Dong, J., (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5):1122\u20131131.","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"2987_CR110","doi-asserted-by":"crossref","unstructured":"Khandelwal, A. (2024). Promptsync: Bridging domain gaps in vision-language models through class-aware prototype alignment and discrimination. CVPR Workshops","DOI":"10.1109\/CVPRW63382.2024.00778"},{"key":"2987_CR111","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Naeem, M.F., Naseer, M., Gool, L.V., & Tombari, F. (2025). In AAAI: Learning to prompt with text only supervision for vision-language models.","DOI":"10.1609\/aaai.v39i4.32444"},{"key":"2987_CR112","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., & Khan, F.S. (2022). Maple: Multi-modal prompt learning. arXiv preprint arXiv:2210.03117.","DOI":"10.1109\/CVPR52729.2023.01832"},{"issue":"6","key":"2987_CR113","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TAI.2021.3110179","volume":"2","author":"Y Kim","year":"2021","unstructured":"Kim, Y., Cho, D., Han, K., Panda, P., & Hong, S. (2021). Domain adaptation without source data. IEEE Transactions on Artificial Intelligence, 2(6), 508\u2013518.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"2987_CR114","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., Dollar, P., & Girshick, R. (2023). Segment anything. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2987_CR115","unstructured":"Kojima, Y., Jiarui, X., & Zou, X., & Wang., X. (2025). Lora-TTT: Low-rank test-time training for vision-language models. In ICML Workshops."},{"key":"2987_CR116","unstructured":"Krasin, I., Duerig, T., Alldrin, N., Ferrari, V., Abu-El-Haija, S., Kuznetsova, A., Rom, H., Uijlings, J., Popov, S., Veit, A., & Belongie, S. (2017). Openimages: A public dataset for large-scale multi-label and multi-class image classification. Dataset available from https:\/\/github.com\/openimages, 2(3):18."},{"key":"2987_CR117","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. ICCV Workshops","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2987_CR118","unstructured":"Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images"},{"key":"2987_CR119","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: A large video database for human motion recognition. ICCV","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2987_CR120","unstructured":"Kundu, J.N., Venkat, N., & Babu, R.V.. (2020). In CVPR: Universal source-free domain adaptation."},{"key":"2987_CR121","unstructured":"Kwon, G., Cai, Z., Ravichandran, A., Bas, E., Bhotika, R., & Soatto, S. (2022). Masked vision and language modeling for multi-modal representation learning arXiv:2208.02131 arXiv preprint."},{"key":"2987_CR122","doi-asserted-by":"crossref","unstructured":"Lafon, M., Hakim, G.A.V., Rambour, C., Desrosier, C., & Thome, N. (2025). Cliptta: Robust contrastive vision-language test-time adaptation. arXiv preprint arXiv:2507.14312.","DOI":"10.52202\/085713-2412"},{"key":"2987_CR123","doi-asserted-by":"crossref","unstructured":"Lan, M., Chen, C., Ke, Y., Wang, X., Feng, L., & Zhang, W. (2024). Proxyclip: Proxy attention improves clip for open-vocabulary segmentation. In ECCV.","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"2987_CR124","doi-asserted-by":"crossref","unstructured":"Lan, M., Chen, C., Ke, Y., Wang, X., Feng, L., & Zhang., W. (2024). Clearclip: Decomposing clip representations for dense vision-language inference. In ECCV.","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"2987_CR125","unstructured":"Laroudie, C., Bursuc, A., Ha, M. L., & Franchi, G. (2023). Improving clip robustness with knowledge distillation and self-training arXiv:2309.10361 arXiv preprint."},{"key":"2987_CR126","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., & Ham, B. (2021). Network quantization with element-wise gradient scaling. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"2987_CR127","unstructured":"Lee, Y., Kim, D., Kang, J., Bang, J., Song, H., & Lee, J.-G. (2025). RA-TTA: Retrieval-augmented test-time adaptation for vision-language models. In ICLR."},{"key":"2987_CR128","doi-asserted-by":"crossref","unstructured":"Lee, H., Seo, G., Choi, W., Jung, G., Song, K., & Jung, J. (2025). Enhancing visual classification using comparative descriptors. In WACV.","DOI":"10.1109\/WACV61041.2025.00515"},{"key":"2987_CR129","unstructured":"Li, Y., Cao, Y., Li, J., Wang, Q., & Wang, S. (2024). Data-efficient clip-powered dual-branch networks for source-free unsupervised domain adaptation. arXiv preprint arXiv:2410.15811."},{"key":"2987_CR130","doi-asserted-by":"crossref","unstructured":"Li, S., Gong, H., Dong, H., Yang, T., Zhengzhong, T., & Zhao, Y. (2025). Dpu: Dynamic prototype updating for multimodal out-of-distribution detection. In CVPR.","DOI":"10.1109\/CVPR52734.2025.00953"},{"key":"2987_CR131","doi-asserted-by":"crossref","unstructured":"Li, L., Guan, H., Qiu, J., & Spratling, M. (2024). One prompt word is enough to boost adversarial robustness for pre-trained vision-language models. In CVPR.","DOI":"10.1109\/CVPR52733.2024.02304"},{"key":"2987_CR132","unstructured":"Li, H., Hu, P., Zhang, Q., Peng, X., Liu, X., & Yang, M. (2024). Test-time adaptation for cross-modal retrieval with query shift. In ICLR."},{"key":"2987_CR133","unstructured":"Li, J., Li, H., Erfani, S., Feng, L., & Bailey, J., & Liu., F. (2024). Visual-text cross alignment: Refining the similarity score in vision-language models. In ICML."},{"key":"2987_CR134","doi-asserted-by":"crossref","unstructured":"Li, X., Li, J., Li, F., Zhu, L., Yang, Y., & Shen, HT. (2025). Generalizing vision-language models to novel domains: A comprehensive survey. arXiv preprint arXiv:2506.18504.","DOI":"10.1145\/3816251"},{"key":"2987_CR135","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, X., Xinyi, F., Zhang, X., Wang, W., Chen, S., & Yang., J. (2024). Promptkd: Unsupervised prompt distillation for vision-language models. In CVPR.","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"2987_CR136","unstructured":"Li, J., Savarese, S., & Hoi, S.C. (2023). Masked unsupervised self-training for label-free image classification. In ICLR."},{"key":"2987_CR137","unstructured":"Li, Y., Su, Y., Goodge, A., Jia, K., & Xu, X. (2025). Efficient and context-aware label propagation for zero-\/few-shot training-free adaptation of vision-language model. In ICLR."},{"key":"2987_CR138","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X., (2017). Person search with natural language description. In CVPR.","DOI":"10.1109\/CVPR.2017.551"},{"key":"2987_CR139","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, M., Tian, Y., Zhang, L., Yongchun, L., Liu, J. & Wang., W. (2024). Wavedn: A wavelet-based training-free zero-shot enhancement for vision-language models. In ACM-MM.","DOI":"10.1145\/3664647.3681559"},{"key":"2987_CR140","doi-asserted-by":"crossref","unstructured":"Li, J., Yu, Z., Du, Z., Zhu, L., & Shen, H. T. (2024). A comprehensive survey on source-free domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence46(8), 5743\u20135762.","DOI":"10.1109\/TPAMI.2024.3370978"},{"key":"2987_CR141","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, D., Du, Z., Zhu, L., Chen, Z., & Li, J. (2025). Pataug: Augmentation of augmentation for test-time adaptation. In Proceedings of the 33rd ACM International Conference on Multimedia, 5080\u20135089.","DOI":"10.1145\/3746027.3755740"},{"key":"2987_CR142","unstructured":"Li, A., Zhuang, L., Long, X., Yao, M., & Wang, S. (2025). Test-time loss landscape adaptation for zero-shot generalization in vision-language models. arXiv preprint arXiv:2501.18864."},{"key":"2987_CR143","unstructured":"Liang, J., Hu, D., & Feng, J. (2020). Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. ICML"},{"key":"2987_CR144","unstructured":"Liang, J., Sheng, L., Wang, Z., He, R., & Tan, T. (2024). Realistic unsupervised clip fine-tuning with universal entropy optimization. In ICML."},{"key":"2987_CR145","doi-asserted-by":"crossref","unstructured":"Liang, V.W., Zhang, Y., Kwon, Y., Yeung, S., & Zou, J.Y. (2022). Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. In NeurIPS.","DOI":"10.52202\/068431-1280"},{"issue":"11","key":"2987_CR146","first-page":"8602","volume":"44","author":"J Liang","year":"2022","unstructured":"Liang, J., Dapeng, H., Wang, Y., He, R., & Feng, J. (2022). Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 8602\u20138617.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2987_CR147","unstructured":"Liang, T., & Davis, J. (2025). Making better mistakes in clip-based zero-shot classification with hierarchy-aware language prompts arXiv:2503.02248 arXiv preprint."},{"issue":"1","key":"2987_CR148","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s11263-024-02181-w","volume":"133","author":"J Liang","year":"2025","unstructured":"Liang, J., He, R., & Tan, T. (2025). A comprehensive survey on test-time adaptation under distribution shifts. International Journal of Computer Vision, 133(1), 31\u201364.","journal-title":"International Journal of Computer Vision"},{"key":"2987_CR149","doi-asserted-by":"crossref","unstructured":"Liberatori, B., Conti, A., Rota, P., Wang, Y., & Ricci, E. (2024). Test-time zero-shot temporal action localization. In CVPR.","DOI":"10.1109\/CVPR52733.2024.01771"},{"key":"2987_CR150","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2987_CR151","doi-asserted-by":"crossref","unstructured":"Liu, M., Dong, H., Kelly, J., Fink, O., & Trapp, M. (2025). Extremely simple multimodal outlier synthesis for out-of-distribution detection and segmentation. arXiv preprint arXiv:2505.16985.","DOI":"10.52202\/085713-4021"},{"key":"2987_CR152","doi-asserted-by":"crossref","unstructured":"Liu, M., Hayes, T.L., Mancini, M., Ricci, E., Volpi, R., & Csurka, G. (2025). In ICIP: Test-time vocabulary adaptation for language-driven object detection.","DOI":"10.1109\/ICIP55913.2025.11084618"},{"key":"2987_CR153","unstructured":"Liu, Y., Hong, Q., Huang, L., Gomez-Villa, A., Goswami, D., Liu, X., van\u00a0de Weijer, J., & Tian, Y. (2025). Continual learning for VLMS: A survey and taxonomy beyond forgetting. arXiv preprint arXiv:2508.04227."},{"key":"2987_CR154","unstructured":"Liu, J., Hu, T., Zhang, Y., Gai, X., Feng, Y., & Liu, Z. (2023). A chatgpt aided explainable framework for zero-shot medical image diagnosis. In ICML Workshops."},{"key":"2987_CR155","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. NeurIPS","DOI":"10.52202\/075280-1516"},{"key":"2987_CR156","doi-asserted-by":"crossref","unstructured":"Liu, Z., Sun, H., Peng, Y., & Zhou, J. (2024). Dart: Dual-modal adaptive online prompting and knowledge retention for test-time adaptation. AAAI","DOI":"10.1609\/aaai.v38i13.29320"},{"key":"2987_CR157","unstructured":"Liu, Z., Sun, M., Zhou, T., Huang, G., & Darrell, T. (2018). Rethinking the value of network pruning arXiv:1810.05270 arXiv preprint."},{"key":"2987_CR158","doi-asserted-by":"crossref","unstructured":"Liu, X., & Zach, C. (2024). Tag: Text prompt augmentation for zero-shot out-of-distribution detection supplementary material. ECCV","DOI":"10.1007\/978-3-031-73464-9_22"},{"key":"2987_CR159","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409","volume":"162","author":"Y Li","year":"2025","unstructured":"Li, Y., Wang, H., Duan, Y., Zhang, J., & Li, X. (2025). A closer look at the explainability of contrastive language-image pre-training. Pattern Recognition, 162, Article 111409.","journal-title":"Pattern Recognition"},{"key":"2987_CR160","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497","volume":"124","author":"X Li","year":"2023","unstructured":"Li, X., Wen, C., Yuan, H., & Zhou, N. (2023). Rs-clip: Zero shot remote sensing scene classification via contrastive vision-language supervision. International Journal of Applied Earth Observation and Geoinformation, 124, Article 103497.","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"2987_CR161","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":"2987_CR162","doi-asserted-by":"crossref","unstructured":"Lyu, M., Li, Y., & Chen, X. (2025). Kl-clip: A k-means learning model for zero-shot anomaly segmentation: M. lyu et al. Multimedia Systems, 31(4):294.","DOI":"10.1007\/s00530-025-01884-5"},{"key":"2987_CR163","unstructured":"Ma, C., Liu, Y., Deng, J., Xie, L., Dong, W., & Xu, C. (2022). Understanding and mitigating overfitting in prompt tuning for vision-language models. arXiv preprint arXiv:2211.02219."},{"key":"2987_CR164","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, J., Guo, S., & Xu, W. (2023). Swapprompt: Test-time prompt adaptation for vision-language models. In NeurIPS.","DOI":"10.52202\/075280-2847"},{"key":"2987_CR165","doi-asserted-by":"crossref","unstructured":"Ma, H., Zhu, Y., Zhang, C., Zhao, P., Baoyuan, W., Huang, L.-K., Qinghua, H., & Wu., B. (2024). Spurious feature eraser: Stabilizing test-time adaptation for vision-language foundation model. In AAAI.","DOI":"10.1609\/aaai.v39i18.34124"},{"key":"2987_CR166","doi-asserted-by":"crossref","unstructured":"Ma, J. (2024). Improved self-training for test-time adaptation. CVPR","DOI":"10.1109\/CVPR52733.2024.02237"},{"key":"2987_CR167","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017). Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083."},{"key":"2987_CR168","doi-asserted-by":"crossref","unstructured":"Maharana, S.K., Zhang, B., Karlinsky, L., Feris, R., & Guo, Y. (2025). Batclip: Bimodal online test-time adaptation for clip. In ICCV.","DOI":"10.1109\/ICCV51701.2025.00154"},{"key":"2987_CR169","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft arXiv:1306.5151 arXiv preprint."},{"key":"2987_CR170","doi-asserted-by":"crossref","unstructured":"Mamunur Rahaman, Md., Ewan, K. A., Millar, E., & Meijering. (2025). Leveraging vision-language embeddings for zero-shot learning in histopathology images. IEEE Journal of Biomedical and Health Informatics,","DOI":"10.1109\/JBHI.2025.3584802"},{"key":"2987_CR171","unstructured":"Mao, C., Geng, S., Yang, J., Wang, X., & Vondrick, C. (2023). Understanding zero-shot adversarial robustness for large-scale models. In ICLR."},{"key":"2987_CR172","doi-asserted-by":"crossref","unstructured":"Martin, S., Huang, Y., Shakeri, F., Pesquet, J.-C., & Ben Ayed, I. (2024). Transductive zero-shot and few-shot clip. CVPR","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"2987_CR173","doi-asserted-by":"crossref","unstructured":"Menghini, C., Delworth, A., & Bach, S. (2023). Enhancing clip with clip: Exploring pseudolabeling for limited-label prompt tuning. In NeurIPS.","DOI":"10.52202\/075280-2665"},{"key":"2987_CR174","unstructured":"Menon, S., & Vondrick, C. (2022). Visual classification via description from large language models arXiv:2210.07183 arXiv preprint."},{"key":"2987_CR175","unstructured":"Menon, S., & Vondrick, C. (2023). Visual classification via description from large language models. ICLR"},{"key":"2987_CR176","doi-asserted-by":"crossref","unstructured":"Miller, K., Mishra, S., Gangrade, A., Saenko, K., & Saligrama, V. (2025). Sparc: Score prompting and adaptive fusion for zero-shot multi-label recognition in vision-language models. In CVPR.","DOI":"10.1109\/CVPR52734.2025.00407"},{"key":"2987_CR177","unstructured":"Mirza, M.J., Karlinsky, L., Lin, W., Possegger, H., Feris, R., & Bischof, H. (2023). Tap: Targeted prompting for task adaptive generation of textual training instances for visual classification. arXiv preprint arXiv:2309.06809."},{"key":"2987_CR178","doi-asserted-by":"crossref","unstructured":"Mirza, M.J., Karlinsky, L., Lin, W., Possegger, H., Kozinski, M., Feris, R., & Bischof, H. (2023). Lafter: Label-free tuning of zero-shot classifier using language and unlabeled image collections. In NeurIPS.","DOI":"10.52202\/075280-0252"},{"key":"2987_CR179","doi-asserted-by":"crossref","unstructured":"Mirza, M. J., Karlinsky, L., Lin, W., Doveh, S., Micorek, J., Kozinski, M., Kuhene, H., & Possegger, H. (2024). Meta-prompting for automating zero-shot visual recognition with llms. ECCV","DOI":"10.1007\/978-3-031-72627-9_21"},{"key":"2987_CR180","unstructured":"Mishra, S., Silva-Rodr\u0131guez, J., Ayed, I.B., Pedersoli, M., & Dolz, J. (2024). Words matter: Leveraging individual text embeddings for code generation in clip test-time adaptation. arXiv preprint arXiv:2411.17002."},{"key":"2987_CR181","doi-asserted-by":"crossref","unstructured":"Mistretta, M., Baldrati, A., Bertini, M., & Bagdanov, A.D. (2024). Improving zero-shot generalization of learned prompts via unsupervised knowledge distillation. In ECCV.","DOI":"10.1007\/978-3-031-72907-2_27"},{"key":"2987_CR182","doi-asserted-by":"crossref","unstructured":"Moayeri, M., Rabbat, M., Ibrahim, M., & Bouchacourt, D. (2024). Embracing diversity: Interpretable zero-shot classification beyond one vector per class. In ACM Conference on Fairness, accountability, and transparency.","DOI":"10.1145\/3630106.3659039"},{"key":"2987_CR183","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N.-G., Lee, S.-W., Fidler, S., Urtasun, R., & Yuille, A. (2014). The role of context for object detection and semantic segmentation in the wild. CVPR","DOI":"10.1109\/CVPR.2014.119"},{"key":"2987_CR184","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Yang, Z., Shi, W., Li, X.L., Fei-Fei, L., Hajishirzi, H., Zettlemoyer, L., Liang, P., Cand\u00e8s, E., & Hashimoto, T. (2025). s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393.","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"2987_CR185","doi-asserted-by":"crossref","unstructured":"Munir, A., Qureshi, F.Z., Khan, M.H., & Ali, M. (2025). Tlac: Two-stage lmm augmented clip for zero-shot classification. In CVPR Workshops.","DOI":"10.1109\/CVPRW67362.2025.00021"},{"key":"2987_CR186","doi-asserted-by":"crossref","unstructured":"Murugesan, B., Silva-Rodr\u00edguez, J., Ayed, I.B., & Dolz, J. (2024). In ECCV: Robust calibration of large vision-language adapters.","DOI":"10.1007\/978-3-031-72691-0_9"},{"key":"2987_CR187","doi-asserted-by":"crossref","unstructured":"Nejjar, I., & Wang, Q., & Fink, O. (2023). Dare-gram: Unsupervised domain adaptation regression by aligning inverse gram matrices. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01130"},{"key":"2987_CR188","unstructured":"Nejjar, I., Dong, H., & Fink, O. (2024). Recall and refine: A simple but effective source-free open-set domain adaptation framework arXiv:2411.12558 arXiv preprint."},{"key":"2987_CR189","unstructured":"Nguyen, K.-B., Bui, P.-N., Choo, H., & Nguyen, D.T. (2025). Adaptive cache enhancement for test-time adaptation of vision-language models. arXiv preprint arXiv:2508.07570."},{"key":"2987_CR190","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., Zisserman, A., (2008). Automated flower classification over a large number of classes. In ICVGIP.","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"2987_CR191","unstructured":"Niu, S., Wu, J., Zhang, Y., Chen, Y., Zheng, S., Zhao, P., & Tan, M. (2022). Efficient test-time model adaptation without forgetting. ICML"},{"key":"2987_CR192","unstructured":"Novack, Z., McAuley, J., Lipton, Z.C., & Garg., S. (2023). Chils: Zero-shot image classification with hierarchical label sets. In ICML."},{"key":"2987_CR193","doi-asserted-by":"crossref","unstructured":"Omkar, M., Parkhi, A., Vedaldi, A., Zisserman, C. V., & Jawahar. (2012). Cats and dogs. CVPR","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2987_CR194","unstructured":"OpenAI Blog. (2023). Introducing chatgpt."},{"key":"2987_CR195","doi-asserted-by":"crossref","unstructured":"Osowiechi, D., Noori, M., Hakim, G. A. V., Yazdanpanah, M., Bahri, A., Cheraghalikhani, M., Dastani, S., Beizaee, F., Ayed, I.B., & Desrosiers, C. (2024). Watt: Weight average test-time adaption of clip. In NeurIPS.","DOI":"10.52202\/079017-1522"},{"key":"2987_CR196","unstructured":"Panella, F., Melatti, V., & Boehm, J. Firenet dataset. http:\/\/www.firenet.xyz. Accessed: 2022-05-17."},{"key":"2987_CR197","doi-asserted-by":"crossref","unstructured":"Parashar, S., Lin, Z., Li, Y., & Kong, S. (2023). Prompting scientific names for zero-shot species recognition. EMNLP","DOI":"10.18653\/v1\/2023.emnlp-main.610"},{"key":"2987_CR198","doi-asserted-by":"crossref","unstructured":"Parashar, S., Lin, Z., Liu, T., Dong, X., Li, Y., Ramanan, D., Caverlee, J., & Kong, S. (2024). The neglected tails in vision-language models. CVPR","DOI":"10.1109\/CVPR52733.2024.01234"},{"key":"2987_CR199","doi-asserted-by":"crossref","unstructured":"Park, H., Gupta, A., & Wong, A. (2024). Test-time adaptation for depth completion. CVPR","DOI":"10.1109\/CVPR52733.2024.01939"},{"key":"2987_CR200","doi-asserted-by":"crossref","unstructured":"Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., & Wang, B. (2019). Moment matching for multi-source domain adaptation. In ICCV.","DOI":"10.1109\/ICCV.2019.00149"},{"key":"2987_CR201","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., & Lazebnik, S. (2015). Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In ICCV.","DOI":"10.1109\/ICCV.2015.303"},{"issue":"3","key":"2987_CR202","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/data3030025","volume":"3","author":"P Porwal","year":"2018","unstructured":"Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., & Meriaudeau, F. (2018). Indian diabetic retinopathy image dataset (IDRID): a database for diabetic retinopathy screening research. Data, 3(3), 25.","journal-title":"Data"},{"key":"2987_CR203","doi-asserted-by":"crossref","unstructured":"Pourpanah, F., Abdar, M., Luo, Y., Zhou, X., Wang, R., Lim, C. P., Wang, X.-Z., Jonathan, Q. M., & Wu. (2022). A review of generalized zero-shot learning methods. IEEE Transactions on Pattern Analysis and Machine Intelligence,45(4), 4051\u20134070.","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"2987_CR204","doi-asserted-by":"crossref","unstructured":"Prabhudesai, M., Ke, T.-W., Alexander Cong Li, Pathak, D., & Fragkiadaki, K. (2023). Diffusion-tta: Test-time adaptation of discriminative models via generative feedback. In NeurIPS.","DOI":"10.52202\/075280-0770"},{"key":"2987_CR205","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., & Farhadi, A. (2023). What does a platypus look like? Generating customized prompts for zero-shot image classification. ICCV","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"2987_CR206","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/RBME.2020.3013489","volume":"14","author":"A Qayyum","year":"2020","unstructured":"Qayyum, A., Qadir, J., Bilal, M., & Al-Fuqaha, A. (2020). Secure and robust machine learning for healthcare: A survey. IEEE Reviews in Biomedical Engineering, 14, 156\u2013180.","journal-title":"IEEE Reviews in Biomedical Engineering"},{"key":"2987_CR207","doi-asserted-by":"crossref","unstructured":"Qian, Q., Xu, Y., Hu, J. (2023). Intra-modal proxy learning for zero-shot visual categorization with clip. In NeurIPS.","DOI":"10.52202\/075280-1107"},{"key":"2987_CR208","doi-asserted-by":"crossref","unstructured":"Qian, Q., & Hu, J. (2024). Online zero-shot classification with clip. ECCV","DOI":"10.1007\/978-3-031-72980-5_27"},{"key":"2987_CR209","doi-asserted-by":"crossref","unstructured":"Qiao, X., Huang, P., Yuan, J., Guo, X., Ye, B., Sun, Z., & Li, X. (2025). Bidirectional prototype-reward co-evolution for test-time adaptation of vision-language models. arXiv preprint arXiv:2503.09394.","DOI":"10.1109\/TMM.2026.3694557"},{"key":"2987_CR210","doi-asserted-by":"crossref","unstructured":"Qiao, X., Zhao, J., Jiang, Y., Guo, X., Sun, Z., Zhang, H., & Li, X. (2025). Class-aware prototype learning with negative contrast for test-time adaptation of vision-language models. arXiv preprint arXiv:2510.19802.","DOI":"10.1109\/TMM.2026.3694557"},{"key":"2987_CR211","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cviu.2017.05.001","volume":"163","author":"W Qi","year":"2017","unstructured":"Qi, W., Teney, D., Wang, P., Shen, C., Dick, A., & Van Den Hengel, A. (2017). Visual question answering: A survey of methods and datasets. Computer Vision and Image Understanding, 163, 21\u201340.","journal-title":"Computer Vision and Image Understanding"},{"key":"2987_CR212","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., & Krueger, G. (2021). Learning transferable visual models from natural language supervision. In ICML."},{"key":"2987_CR213","doi-asserted-by":"crossref","unstructured":"Rahman, U., Imam, R., Yaqub, M., Boulbaba Ben Amor, D., & Mahapatra. (2025). Can language-guided unsupervised adaptation improve medical image classification using unpaired images and texts? In ISBI","DOI":"10.1109\/ISBI60581.2025.10981057"},{"key":"2987_CR214","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., Chen, G., Tang, Y., Zhu, Z., Huang, G., Zhou, J., & Lu, J. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2987_CR215","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? In ICML"},{"key":"2987_CR216","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. CVPR","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2987_CR217","unstructured":"Romera, B., Paredes, & Torr, P. (2015). An embarrassingly simple approach to zero-shot learning. ICML"},{"key":"2987_CR218","unstructured":"Rostamzadeh, N., Hosseini, S., Boquet, T., Stokowiec, W., Zhang, Y., Jauvin, C., & Pal, C. (2018). Fashion-gen: The generative fashion dataset and challenge. arXiv preprint arXiv:1806.08317."},{"key":"2987_CR219","doi-asserted-by":"crossref","unstructured":"Roth, K., Kim, J.M., Koepke, A., Vinyals, O., Schmid, C., & Akata, Z. (2023). Waffling around for performance: Visual classification with random words and broad concepts. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"2987_CR220","doi-asserted-by":"crossref","unstructured":"Saenko, K., Kulis, B., Fritz, M., & Darrell, T. (2010). Adapting visual category models to new domains. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"2987_CR221","doi-asserted-by":"crossref","unstructured":"Saha, O., Lawrence, L., Van Horn, G., & Maji, S. (2025). Generate, transduct, adapt: Iterative transduction with VLMS. ICCV","DOI":"10.1109\/ICCV51701.2025.00135"},{"key":"2987_CR222","doi-asserted-by":"crossref","unstructured":"Samadh, J.A., Gani, M.H., Hussein, N., Khattak, M.U., Naseer, M.M., Khan, F.S., & Khan, S.H. (2023). Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization. In NeurIPS.","DOI":"10.52202\/075280-3525"},{"key":"2987_CR223","unstructured":"Sarkar, D., Chakrabartty, A., Bhanja, B., & Das, A. (2024). Active test time prompt learning in vision-language models."},{"key":"2987_CR224","unstructured":"Schlarmann, C., Naman Deep, Singh, F., Croce, M., & Hein. (2024). Robust clip: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models. ICML"},{"key":"2987_CR225","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., & Wortsman, M. (2022). Laion-5b: An open large-scale dataset for training next generation image-text models. NeurIPS","DOI":"10.52202\/068431-1833"},{"key":"2987_CR226","unstructured":"Seo, M., Cho, S., Lee, M., Misra, D., Choi, H., Kim, S.\u00a0J., & Choi, J. (2024). Just say the name: Online continual learning with category names only via data generation. arXiv preprint arXiv:2403.10853."},{"key":"2987_CR227","unstructured":"Shafiullah, N. M. M., Paxton, C., Pinto, L., Chintala, S., & Szlam, A. (2022). Clip-fields: Weakly supervised semantic fields for robotic memory arXiv:2210.05663 arXiv preprint."},{"key":"2987_CR228","doi-asserted-by":"crossref","unstructured":"Shao, T., Tian, Z., Zhao, H., & Su, J. (2024). Explore the potential of clip for training-free open vocabulary semantic segmentation. ECCV","DOI":"10.1007\/978-3-031-73016-0_9"},{"key":"2987_CR229","doi-asserted-by":"crossref","unstructured":"Sharifdeen, A., Munir, M.A., Baliah, S., Khan, S., & Khan, M.H. (2025). O-tpt: Orthogonality constraints for calibrating test-time prompt tuning in vision-language models. In CVPR.","DOI":"10.1109\/CVPR52734.2025.01857"},{"key":"2987_CR230","doi-asserted-by":"crossref","unstructured":"Sheng, L., Liang, J., He, R., Wang, Z., & Tan, T. (2025). The illusion of progress? A critical look at test-time adaptation for vision-language models. arXiv preprint arXiv:2506.24000.","DOI":"10.52202\/085713-4167"},{"key":"2987_CR231","doi-asserted-by":"crossref","unstructured":"Sheng, L., Liang, J., Wang, Z., He, R. (2025). R-TPT: Improving adversarial robustness of vision-language models through test-time prompt tuning. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02788"},{"key":"2987_CR232","doi-asserted-by":"crossref","unstructured":"Shen, S., Zhu, Z., Fan, L., Zhang, H., & Wu, X. (2024). Diffclip: Leveraging stable diffusion for language grounded 3d classification. WACV","DOI":"10.1109\/WACV57701.2024.00356"},{"key":"2987_CR233","unstructured":"Shihab Aaqil Ahamed, Udaya, S., Thanthrige, R., Rodrigo, M. H., & Khan. (2025). A-TPT: Angular diversity calibration properties for test-time prompt tuning of vision-language models arXiv:2510.26441 arXiv preprint."},{"key":"2987_CR234","doi-asserted-by":"crossref","unstructured":"Shin, G., Xie, W., & Albanie, S. (2022). Reco: Retrieve and co-segment for zero-shot transfer. In NeurIPS.","DOI":"10.52202\/068431-2446"},{"key":"2987_CR235","doi-asserted-by":"crossref","unstructured":"Shin, C., Zhao, J., Cromp, S., & Vishwakarma, H., & Sala., F. (2024). Otter: Effortless label distribution adaptation of zero-shot models. In NeurIPS.","DOI":"10.52202\/079017-1399"},{"key":"2987_CR236","doi-asserted-by":"crossref","unstructured":"Shipard, J., Wiliem, A., Thanh, K.N., Xiang, W., & Fookes, C. (2023). Diversity is definitely needed: Improving model-agnostic zero-shot classification via stable diffusion. In CVPR.","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"2987_CR237","doi-asserted-by":"crossref","unstructured":"Shu, M., Nie, W., Huang, D-A., Yu, Z., Goldstein, T., Anandkumar, A., & Xiao, C (2022). Test-time prompt tuning for zero-shot generalization in vision-language models. In NeurIPS.","DOI":"10.52202\/068431-1038"},{"key":"2987_CR238","doi-asserted-by":"crossref","unstructured":"Silva, S., Ali, E., Arora, C., & Khan, M. H. (2025). Microclip: Unsupervised clip adaptation via coarse-fine token fusion for fine-grained image classification arXiv:2510.02270 arXiv preprint.","DOI":"10.18653\/v1\/2026.findings-acl.1664"},{"key":"2987_CR239","unstructured":"Singh, A., Marjit, S., Lin, W., Gavrikov, P., Yeung-Levy, S., Kuehne, H., Feris, R., Doveh, S., Glass, J., & Mirza, M. J. (2025). Ttrv: Test-time reinforcement learning for vision language models arXiv:2510.06783 arXiv preprint."},{"key":"2987_CR240","unstructured":"Snell, C., Lee, J., Xu, K., & Kumar, A. (2024). Scaling llm test-time compute optimally can be more effective than scaling model parameters arXiv:2408.03314 arXiv preprint."},{"key":"2987_CR241","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E.D., Kurakin, A., & Li, C.-L. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In NeurIPS."},{"key":"2987_CR242","doi-asserted-by":"crossref","unstructured":"Song, J., Lee, J., Kweon, I.S., Choi., S. (2023). Ecotta: Memory-efficient continual test-time adaptation via self-distilled regularization. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01147"},{"key":"2987_CR243","unstructured":"Soomro, K., Amir Roshan Zamir, M., & Shah. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild arXiv:1212.0402 arXiv preprint."},{"key":"2987_CR244","unstructured":"Sreenivas, M., & Biswas, S. (2024). Effectiveness of vision language models for open-world single image test time adaptation arXiv:2406.00481 arXiv preprint."},{"key":"2987_CR245","unstructured":"Su, L., & Balogh, A. (2025). Atac: Augmentation-based test-time adversarial correction for clip arXiv:2511.17362 arXiv preprint."},{"key":"2987_CR246","doi-asserted-by":"crossref","unstructured":"Sui, E., Wang, X., & Yeung-Levy, S. (2024). Just shift it: Test-time prototype shifting for zero-shot generalization with vision-language models. In WACV.","DOI":"10.1109\/WACV61041.2025.00090"},{"key":"2987_CR247","unstructured":"Sun, W., Du, Y., Liu, G., Kompella, R., & Snoek, C.\u00a0G., (2024). Training-free semantic segmentation via LLM-supervision. arXiv preprint arXiv:2404.00701."},{"key":"2987_CR248","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., & Cao, Y. (2023). Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389."},{"key":"2987_CR249","doi-asserted-by":"crossref","unstructured":"Sun, J., Ibrahim, M., Hall, M., Evtimov, I., Mao, Z.M., Ferrer, C.C., & Hazirbas, C. (2023). VPA: Fully test-time visual prompt adaptation. In ACM-MM.","DOI":"10.1145\/3581783.3611835"},{"key":"2987_CR250","doi-asserted-by":"crossref","unstructured":"Sun, H., Cao, Y., Dong, H., & Fink, O. (2025). Unseen visual anomaly generation. CVPR","DOI":"10.1109\/CVPR52734.2025.02375"},{"key":"2987_CR251","doi-asserted-by":"crossref","unstructured":"Tamjidi, M., Dastmalchi, H., Alimoradijazi, M., & Cheraghian, A. (2025). Adapt-as-you-walk through the clouds: Training-free online test-time adaptation of 3d vision-language foundation models arXiv:2511.15311 arXiv preprint Aijun An, and Morteza Saberi.","DOI":"10.1609\/aaai.v40i11.37888"},{"key":"2987_CR252","unstructured":"Tanwisuth, K., Zhang, S., Zheng, H., He, P., & Zhou, M. (2023). Pouf: Prompt-oriented unsupervised fine-tuning for large pre-trained models. In ICML."},{"key":"2987_CR253","doi-asserted-by":"crossref","unstructured":"Tong, B., Lai, H., Pan, Y., & Yin, J. (2025). On the zero-shot adversarial robustness of vision-language models: A truly zero-shot and training-free approach. In CVPR.","DOI":"10.1109\/CVPR52734.2025.01855"},{"key":"2987_CR254","doi-asserted-by":"crossref","unstructured":"Tong, B., Song, K., & Lai, H. (2024). Test-time alignment-enhanced adapter for vision-language models arXiv:2411.15735 arXiv preprint.","DOI":"10.1109\/ICASSP49660.2025.10888937"},{"key":"2987_CR255","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., & Rodriguez, A. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"2987_CR256","doi-asserted-by":"crossref","unstructured":"Udandarao, V., Gupta, A., & Albanie, S. (2023). Sus-x: Training-free name-only transfer of vision-language models. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"2987_CR257","unstructured":"Urquhart Allingham, J., Ren, J., Michael, W., Dusenberry, X., Gu, Y., Cui, D., Tran, J. Z., Liu, B., & Lakshminarayanan. (2023). A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models. ICML"},{"key":"2987_CR258","doi-asserted-by":"crossref","unstructured":"Van Horn, G., Aodha, O.M., Song, Y., Cui, Y., Sun, C., Shepard, A., Adam, H., Perona, P., & Belongie, S. (2018). In CVPR: The inaturalist species classification and detection dataset.","DOI":"10.1109\/CVPR.2018.00914"},{"key":"2987_CR259","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). In NeurIPS: Attention is all you need."},{"key":"2987_CR260","doi-asserted-by":"crossref","unstructured":"Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017). Deep hashing network for unsupervised domain adaptation. CVPR","DOI":"10.1109\/CVPR.2017.572"},{"key":"2987_CR261","doi-asserted-by":"crossref","unstructured":"Verma, V.K., Arora, G., Mishra, A., & Rai, P. (2018). In CVPR: Generalized zero-shot learning via synthesized examples.","DOI":"10.1109\/CVPR.2018.00450"},{"key":"2987_CR262","unstructured":"Vipula Rawte, A., Sheth, A., & Das. (2023). A survey of hallucination in large foundation models arXiv:2309.05922 arXiv preprint."},{"key":"2987_CR263","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset."},{"key":"2987_CR264","doi-asserted-by":"crossref","unstructured":"Wallingford, M., Ramanujan, V., Fang, A., Kusupati, A., Mottaghi, R., Kembhavi, A., Schmidt, L., & Farhadi, A. (2023). Neural priming for sample-efficient adaptation. In NeurIPS.","DOI":"10.52202\/075280-2861"},{"key":"2987_CR265","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, K., Zhang, J., Chen, J., & Ma, X. (2024). Tapt: Test-time adversarial prompt tuning for robust inference in vision-language models. In CVPR.","DOI":"10.1109\/CVPR52734.2025.01854"},{"key":"2987_CR266","unstructured":"Wang, H., Ge, S., Lipton, Z., & Xing, E.P. (2019). Learning robust global representations by penalizing local predictive power. In NeurIPS."},{"key":"2987_CR267","doi-asserted-by":"crossref","unstructured":"Wang, Z., Gong, D., Wang, S., Huang, Z., & Luo, Y. (2025). Is less more? Exploring token condensation as training-free test-time adaptation. In ICCV.","DOI":"10.1109\/ICCV51701.2025.00021"},{"key":"2987_CR268","unstructured":"Wang, Z., Liang, J., Sheng, L., He, R., Wang, Z., & Tan, T. (2024). A hard-to-beat baseline for training-free clip-based adaptation. In ICLR."},{"key":"2987_CR269","doi-asserted-by":"crossref","unstructured":"Wang, F., Mei, J.,& Yuille, A. (2024). Sclip: Rethinking self-attention for dense vision-language inference. In ECCV.","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"2987_CR270","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., & Darrell, T. (2021). Tent: Fully test-time adaptation by entropy minimization. In ICLR."},{"key":"2987_CR271","doi-asserted-by":"crossref","unstructured":"Wang, W., Vincent, W., Zheng, H., Yu, C., & Miao. (2019). A survey of zero-shot learning: Settings, methods, and applications. ACM Transactions on Intelligent Systems and Technology 10(2), 1\u201337.","DOI":"10.1145\/3293318"},{"key":"2987_CR272","doi-asserted-by":"crossref","unstructured":"Wang, S., Wan, Q., Gao, J., & Zeng, Z. (2025). Language-driven multi-label zero-shot learning with semantic granularity. In ICCV.","DOI":"10.1109\/ICCV51701.2025.00191"},{"key":"2987_CR273","doi-asserted-by":"crossref","unstructured":"Wang, Q., Fink, O., Van Gool, L., & Dai, D. (2022). Continual test-time domain adaptation. CVPR","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"2987_CR274","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111300","volume":"161","author":"F Wang","year":"2025","unstructured":"Wang, F., Han, Z., Liu, X., Yin, Y., & Gao, X. (2025). Ctpt: Continual test-time prompt tuning for vision-language models. Pattern Recognition, 161, Article 111300.","journal-title":"Pattern Recognition"},{"issue":"3","key":"2987_CR275","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1007\/s11263-024-02213-5","volume":"133","author":"Z Wang","year":"2025","unstructured":"Wang, Z., Luo, Y., Zheng, L., Chen, Z., Wang, S., & Huang, Z. (2025). In search of lost online test-time adaptation: A survey. International Journal of Computer Vision, 133(3), 1106\u20131139.","journal-title":"International Journal of Computer Vision"},{"key":"2987_CR276","doi-asserted-by":"crossref","unstructured":"Wang, S., Song, L., Shimizu, R., Goto, M., & Wu, H. (2025). Attributed synthetic data generation for zero-shot domain-specific image classification. ICME","DOI":"10.1109\/ICME59968.2025.11209782"},{"key":"2987_CR277","doi-asserted-by":"crossref","unstructured":"Wang, R., Zuo, H., Fang, Z., & Lu, J. (2024). Towards robustness prompt tuning with fully test-time adaptation for clip\u2019s zero-shot generalization. ACM-MM","DOI":"10.1145\/3664647.3681213"},{"key":"2987_CR278","doi-asserted-by":"crossref","unstructured":"Wang, R., Zuo, H., Fang, Z., & Lu, J. (2024). Prompt-based memory bank for continual test-time domain adaptation in vision-language models. IJCNN","DOI":"10.1109\/IJCNN60899.2024.10650069"},{"key":"2987_CR279","unstructured":"Weber, M., Xie, J., Collins, M., Zhu, Y., Voigtlaender, P., Adam, H., Green, B., Geiger, A., Leibe, B., Cremers, D., & Osep, A., (2021). Step: Segmenting and tracking every pixel. arXiv preprint arXiv:2102.11859."},{"key":"2987_CR280","doi-asserted-by":"crossref","unstructured":"Wei, C. (2024). Enhancing fine-grained image classifications via cascaded vision language models. EMNLP Findings","DOI":"10.18653\/v1\/2024.findings-emnlp.102"},{"key":"2987_CR281","doi-asserted-by":"crossref","unstructured":"Wen, J., Liu, R., Zheng, N., Zheng, Q., Gong, Z., & Yuan, J. (2019). Exploiting local feature patterns for unsupervised domain adaptation. In AAAI.","DOI":"10.1609\/aaai.v33i01.33015401"},{"key":"2987_CR282","doi-asserted-by":"crossref","unstructured":"Wysocza\u0144ska, M., Ramamonjisoa, M., Trzci\u0144ski, T., & Sim\u00e9oni, O. (2024). Clip-diy: Clip dense inference yields open-vocabulary semantic segmentation for-free. In WACV.","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"2987_CR283","doi-asserted-by":"crossref","unstructured":"Xian, Y., Sharma, S., Schiele, B., & Akata, Z. (2019). f-vaegan-d2: A feature generating framework for any-shot learning. CVPR","DOI":"10.1109\/CVPR.2019.01052"},{"key":"2987_CR284","doi-asserted-by":"crossref","unstructured":"Xian, Y., Schiele, B., & Akata, Z. (2017). Zero-shot learning-the good, the bad and the ugly. CVPR","DOI":"10.1109\/CVPR.2017.328"},{"key":"2987_CR285","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger., K., A., Oliva., A., & Torralba., A., (2010). Sun database: Large-scale scene recognition from abbey to zoo. In CVPR.","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"2987_CR286","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Shen, J., Derakhshani, M.M., Liao, S., & Snoek, C.GM. (2024). In CVPR: Any-shift prompting for generalization over distributions.","DOI":"10.1109\/CVPR52733.2024.01314"},{"key":"2987_CR287","unstructured":"Xiao, Z., Yan, S., Hong, J., Cai, J., Jiang, X., Hu, Y., Shen, J., Wang, C., & Snoek, C.G.M. (2025). Dynaprompt: Dynamic test-time prompt tuning. In ICLR."},{"key":"2987_CR288","unstructured":"Xiao, Z., Cees, G. M., & Snoek. (2024). Beyond model adaptation at test time: A survey arXiv:2411.03687 arXiv preprint."},{"key":"2987_CR289","unstructured":"Xie, J., Mao, W., Bai, Z., Zhang, DJ., Wang, W., Lin, K.Q., Gu, Y., Chen, Z., Yang, Z., & Shou, M.Z. (2024). Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528."},{"key":"2987_CR290","doi-asserted-by":"crossref","unstructured":"Xing, S., Zhao, Z., & Sebe., N. (2025). Clip is strong enough to fight back: Test-time counterattacks towards zero-shot adversarial robustness of clip. In CVPR.","DOI":"10.1109\/CVPR52734.2025.01413"},{"key":"2987_CR291","unstructured":"Xu, Q., Chen, W., Hu, Z., Li, H., & Tai, Y. (2025). Otfusion: Bridging vision-only and vision-language models via optimal transport for transductive zero-shot learning. arXiv preprint arXiv:2506.13723."},{"key":"2987_CR292","doi-asserted-by":"crossref","unstructured":"Yang, C., Shen, Y., Zhang, Z., Xu., Y., Zhu., J., Wu., Z., & Zhou., B. (2023). One-shot generative domain adaptation. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00711"},{"key":"2987_CR293","doi-asserted-by":"crossref","unstructured":"Yan, H., & Guo, Y. (2024). Lightweight unsupervised federated learning with pretrained vision language model. International Workshop on Trustworthy Federated Learning","DOI":"10.1007\/978-3-031-82240-7_11"},{"key":"2987_CR294","unstructured":"Yan, R., Qu, H., Shu, X., Li, W., Tang, J., & Tan, T. (2024). Dts-tpt: dual temporal-sync test-time prompt tuning for zero-shot activity recognition. IJCAI"},{"key":"2987_CR295","doi-asserted-by":"crossref","unstructured":"Yan, R., Wang, J., Qu, H., Du, X., Zhang, D., Tang, J., & Tan, T. (2025). Test-v: Test-time support-set tuning for zero-shot video classification arXiv:2502.00426 arXiv preprint.","DOI":"10.24963\/ijcai.2025\/239"},{"key":"2987_CR296","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., Liang, X., Li, Z., Jiang, X., & Xu, C. (2021). Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783."},{"key":"2987_CR297","doi-asserted-by":"crossref","unstructured":"Yi, J., Pan, R., Yang, J., & Yang, X. (2025). Mint: Memory-infused prompt tuning at test-time for clip. arXiv preprint arXiv:2506.03190.","DOI":"10.1007\/978-981-95-4097-6_10"},{"key":"2987_CR298","doi-asserted-by":"crossref","unstructured":"Yin, J., Zhang, X., Wu, L., & Wang, X. (2024). In-context prompt learning for test-time vision recognition with frozen vision-language model. arXiv preprint arXiv:2403.06126.","DOI":"10.1016\/j.patcog.2025.111359"},{"key":"2987_CR299","unstructured":"Yin, X., Wang, Q., Cao, B., & Hu, Q. (2024). S3: Synonymous semantic space for improving zero-shot generalization of vision-language models arXiv:2412.04925 arXiv preprint."},{"key":"2987_CR300","unstructured":"Yin, X., Wang, Q., & Hu, Q. (2025). Constrained prompt enhancement for improving zero-shot generalization of vision-language models arXiv:2508.17417 arXiv preprint."},{"key":"2987_CR301","doi-asserted-by":"crossref","unstructured":"Yi, C., Ren, L., De-Chuan Zhan, H.-J., & Ye. (2024). Leveraging cross-modal neighbor representation for improved clip classification. CVPR","DOI":"10.1109\/CVPR52733.2024.02587"},{"key":"2987_CR302","unstructured":"Yoon, H.S., Yoon, E., Tee, J.T.J., Hasegawa-Johnson, M., Li, Y., & Yoo, C.D. (2024). C-tpt: Calibrated test-time prompt tuning for vision-language models via text feature dispersion. In ICLR."},{"key":"2987_CR303","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., & Luo, J. (2016). Image captioning with semantic attention. CVPR","DOI":"10.1109\/CVPR.2016.503"},{"key":"2987_CR304","doi-asserted-by":"crossref","unstructured":"Yousaf, A., & Shah, M. (2025). Enhancing vision-language models for zero-shot video action recognition via visual-textual refinement and improved interpretability. ICCV Workshops","DOI":"10.1109\/ICCVW69036.2025.00040"},{"key":"2987_CR305","doi-asserted-by":"crossref","unstructured":"Zanella, M., & Ben Ayed, I. (2024). On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning? In CVPR.","DOI":"10.1109\/CVPR52733.2024.02245"},{"key":"2987_CR306","doi-asserted-by":"crossref","unstructured":"Zanella, M., & Ben Ayed, I. (2024). Low-rank few-shot adaptation of vision-language models. CVPR Workshops","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"2987_CR307","doi-asserted-by":"crossref","unstructured":"Zanella, M., Fuchs, C., Vleeschouwer, C. D., & Ben Ayed, I. (2025). Realistic test-time adaptation of vision-language models. CVPR","DOI":"10.1109\/CVPR52734.2025.02337"},{"key":"2987_CR308","doi-asserted-by":"crossref","unstructured":"Zanella, M., G\u00e9rin, B., & Ayed, I. (2024). Boosting vision-language models with transduction. NeurIPS","DOI":"10.52202\/079017-1988"},{"key":"2987_CR309","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., & Beyer, L. (2023). Sigmoid loss for language image pre-training. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"2987_CR310","doi-asserted-by":"crossref","unstructured":"Zhai, H., Chen, X., Zhang, C., Sha, T., & Li, R. (2025). Mitigating cache noise in test-time adaptation for large vision-language models. ICLR Workshops","DOI":"10.1109\/ICME59968.2025.11209257"},{"key":"2987_CR311","doi-asserted-by":"crossref","unstructured":"Zhang,K., Zhou, R., Adhikarla, E., Yan, Z., Liu, Y., Yu, J., Liu, Z., Chen, X., Davison, B.D., Ren, H., & Huang, J., (2024). A generalist vision\u2013language foundation model for diverse biomedical tasks. Nature Medicine, 1\u201313.","DOI":"10.1038\/s41591-024-03185-2"},{"key":"2987_CR312","unstructured":"Zhang, R., Fang, R., Gao, P., Zhang, W., Li, K., Dai, J., Qiao, Y., & Li, H. (2021). Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930."},{"key":"2987_CR313","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Zhang, X., Shao, L., & Lu, S. (2024). Historical test-time prompt tuning for vision foundation models. In NeurIPS.","DOI":"10.52202\/079017-0410"},{"key":"2987_CR314","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Kim, Y., Choi, Y.-G., Kim, H., Liu, H., & Hong, S. (2025). Backpropagation-free test-time adaptation via probabilistic gaussian alignment. arXiv preprint arXiv:2508.15568.","DOI":"10.52202\/085713-2562"},{"key":"2987_CR315","doi-asserted-by":"crossref","unstructured":"Zhang, C., Kunlun, X., Liu, Z., Peng, Y., & Zhou, J. (2025). SCAP: Transductive test-time adaptation via supportive clique-based attribute prompting. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02795"},{"key":"2987_CR316","doi-asserted-by":"crossref","unstructured":"Zhang, C., Stepputtis, S., Sycara, K., & Xie, Y. (2024). Dual prototype evolving for test-time generalization of vision-language models. In NeurIPS.","DOI":"10.52202\/079017-1010"},{"key":"2987_CR317","doi-asserted-by":"crossref","unstructured":"Zhang, A., Tianyuan, Yu., Bai, L., Tang, J., Guo, Y., Ruan, Y., Zhou, Y., & Lu., Z. (2025). Cola: Context-aware language-driven test-time adaptation. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2025.3607634"},{"key":"2987_CR318","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wang, J., Guo, H., Dai, T., Chen, B., & Xia, S.-T. (2024). Boostadapter: Improving vision-language test-time adaptation via regional bootstrapping. In NeurIPS.","DOI":"10.52202\/079017-2165"},{"key":"2987_CR319","unstructured":"Zhang, J., Wei, Q., Liu, F., & Feng., L. (2024). Candidate pseudolabel learning: Enhancing vision-language models by prompt tuning with unlabeled data. In ICML."},{"key":"2987_CR320","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai., J., Qiao., Y., & Li., H. (2022). Tip-adapter: Training-free adaption of clip for few-shot classification. In ECCV.","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"2987_CR321","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, C., Hu, X., & He, Z. (2023). Unsupervised prototype adapter for vision-language models. In PRCV.","DOI":"10.1007\/978-981-99-8429-9_16"},{"key":"2987_CR322","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhao, M., Liu, J., Zhang, F., Xu, Y., & Zha, Z.-J. (2025). Hierarchical knowledge prompt tuning for multi-task test-time adaptation. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02842"},{"key":"2987_CR323","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, W., Tang, H., Ma, Z., Zhou, K., & Zhang, L. (2024). Dual memory networks: A versatile adaptation approach for vision-language models. In CVPR.","DOI":"10.1109\/CVPR52733.2024.02713"},{"issue":"8","key":"2987_CR324","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., & Shijian, L. (2024). Vision-language models for vision tasks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8), 5625\u20135644.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2987_CR325","doi-asserted-by":"crossref","unstructured":"Zhang, D.-C., Zhou, Z., & Li, Y.-F. (2024). Robust test-time adaptation for zero-shot prompt tuning. AAAI","DOI":"10.1609\/aaai.v38i15.29611"},{"key":"2987_CR326","unstructured":"Zhao, S., Wang, X., Zhu, L., & Yang, Y. (2023). Test-time adaptation with clip reward for zero-shot generalization in vision-language models. ICLR"},{"key":"2987_CR327","doi-asserted-by":"crossref","unstructured":"Zhen, L., Hu, P., Wang, X., & Peng, D. (2019). Deep supervised cross-modal retrieval. In CVPR.","DOI":"10.1109\/CVPR.2019.01064"},{"key":"2987_CR328","doi-asserted-by":"publisher","first-page":"1908","DOI":"10.1109\/TIP.2025.3546840","volume":"34","author":"L Zhihe","year":"2025","unstructured":"Zhihe, L., Bai, J., Li, X., Xiao, Z., & Wang, X. (2025). Task-to-instance prompt learning for vision-language models at test time. IEEE Transactions on Image Processing, 34, 1908\u20131920.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2987_CR329","unstructured":"Zhiyuan Ren, Y., Su, X., & Liu. (2023). Chatgpt-powered hierarchical comparisons for image classification. NeurIPS"},{"key":"2987_CR330","unstructured":"Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., He, L., Peng, H. (2024). A comprehensive survey on pretrained foundation models: A history from Bert to Chatgpt. International Journal of Machine Learning and Cybernetics, 1\u201365."},{"key":"2987_CR331","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C., & Dai, B. (2022). Extract free dense labels from clip: In ECCV.","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"2987_CR332","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Ren, J., Li, F., Zabih, R., & Lim, S.N. (2023). Test-time distribution normalization for contrastively learned visual-language models. In NeurIPS.","DOI":"10.52202\/075280-2040"},{"key":"2987_CR333","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., & Liu, Z. (2022). In CVPR: Conditional prompt learning for vision-language models.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2987_CR334","doi-asserted-by":"crossref","unstructured":"Zhou, L., Ye, M., Li, S., Li, N., Wu, J., Zhu, X., Deng, L., Liu, H., Luo, J., & Lei, Z. (2025). Bayesian test-time adaptation for object recognition and detection with vision-language models. arXiv preprint arXiv:2510.02750.","DOI":"10.1109\/CVPR52734.2025.02792"},{"key":"2987_CR335","doi-asserted-by":"crossref","unstructured":"Zhou, L., Ye, M., Li, S., Li, N., Zhu, X., Deng, L., Liu, H., & Lei, Z. (2025). Bayesian test-time adaptation for vision-language models. In CVPR.","DOI":"10.1109\/CVPR52734.2025.02792"},{"issue":"6","key":"2987_CR336","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2017). Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1452\u20131464.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2987_CR337","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"},{"key":"2987_CR338","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127, 302\u2013321.","journal-title":"International Journal of Computer Vision"},{"key":"2987_CR339","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Ji, Y., Zhao, Z., Gangshan, W., & Wang, L. (2024). Awt: Transferring vision-language models via augmentation, weighting, and transportation. In NeurIPS.","DOI":"10.52202\/079017-0804"},{"key":"2987_CR340","unstructured":"Zhu, Y., Zhang, G., Xu, C., Shen, H., Chen, X., Wu, G., & Wang, L. (2024). Efficient test-time prompt tuning for vision-language models. arXiv preprint arXiv:2408.05775."},{"issue":"1","key":"2987_CR341","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40051-3","volume":"19","author":"B Zhu","year":"2025","unstructured":"Zhu, B., & Zhang, H. (2025). Debiasing vision-language models for vision tasks: A survey. Frontiers of Computer Science, 19(1), Article 191321.","journal-title":"Frontiers of Computer Science"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02987-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02987-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02987-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:19:05Z","timestamp":1787368745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02987-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":341,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2987"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02987-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"14 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"389"}}