{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:17:37Z","timestamp":1742966257297,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729034"},{"type":"electronic","value":"9783031729041"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72904-1_25","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:29:26Z","timestamp":1732109366000},"page":"425-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["uCAP: An Unsupervised Prompting Method for\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"A. Tuan","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai Sheng","family":"Tai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bor-Chun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satya Narayan","family":"Shukla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanchao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tai-Peng","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"25_CR1","unstructured":"Chen, G., Yao, W., Song, X., Li, X., Rao, Y., Zhang, K.: PLOT: prompt learning with optimal transport for vision-language models. In: ICLR (2023)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"25_CR6","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised prompt learning for vision-language models. arXiv (2022)"},{"key":"25_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"25_CR8","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Lee, D., Song, S., Suh, J., Choi, J., Lee, S., Kim, H.J.: Read-only prompt optimization for vision-language few-shot learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Li, F.F., Andreeto, M., Ranzato, M., Perona, P.: Caltech 101 (2022). https:\/\/doi.org\/10.22002\/D1.20086","DOI":"10.22002\/D1.20086"},{"key":"25_CR11","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"25_CR12","unstructured":"Li, X., Wang, Z., Xie, C.: CLIPA-v2: scaling CLIP training with 81.1% zero-shot ImageNet accuracy within a \\$10, 000 budget; an extra \\$4, 000 unlocks 81.8% accuracy. arXiv (2023)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Lu, Y., Liu, J., Zhang, Y., Liu, Y., Tian, X.: Prompt distribution learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"25_CR14","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: ICLR (2023)"},{"key":"25_CR15","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: ClipCap: CLIP prefix for image captioning. arXiv (2021)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, A.T., Nguyen-Tang, T., Lim, S.N., Torr, P.H.: TIPI: test time adaptation with transformation invariance. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02314"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Pratt, S., Liu, R., Farhadi, A.: What does a platypus look like? Generating customized prompts for zero-shot image classification. In: ICCV (2022)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"25_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"25_CR20","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to ImageNet? In: ICML (2019)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"3","key":"25_CR22","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"25_CR23","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv (2012)"},{"key":"25_CR24","unstructured":"Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A., Hardt, M.: Test-time training with self-supervision for generalization under distribution shifts. In: ICML (2020)"},{"key":"25_CR25","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization. In: ICLR (2021)"},{"key":"25_CR26","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: NeurIPS (2019)"},{"key":"25_CR27","unstructured":"Welling, M., Teh, Y.W.: Bayesian learning via stochastic gradient Langevin dynamics. In: ICML (2011)"},{"key":"25_CR28","unstructured":"Wilson, A.G., Izmailov, P.: Deep ensembles as approximate Bayesian inference (2021)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: SUN database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"25_CR30","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv (2022)"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"25_CR32","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV 130(9), 2337\u20132348 (2022)","journal-title":"IJCV"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72904-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T19:52:01Z","timestamp":1742068321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72904-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031729034","9783031729041"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72904-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}