{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:31Z","timestamp":1776888631761,"version":"3.51.2"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72980-5_27","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"462-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Online Zero-Shot Classification with\u00a0CLIP"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8661-1169","authenticated-orcid":false,"given":"Qi","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5869-3549","authenticated-orcid":false,"given":"Juhua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"27_CR2","unstructured":"Boyd, S.P., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2014)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"27_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: ICLR. OpenReview.net (2021)"},{"key":"27_CR5","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: CVPR Workshop, p. 178. IEEE (2004)"},{"key":"27_CR6","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. CoRR abs\/2110.04544 (2021)"},{"key":"27_CR7","unstructured":"Hazan, E.: Introduction to online convex optimization. CoRR abs\/1909.05207 (2019)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 12(7), 2217\u20132226 (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: ICCV Workshop, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"27_CR11","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"27_CR12","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Nilsback, M., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP, pp. 722\u2013729. IEEE Computer Society (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Qian, Q., Shang, L., Sun, B., Hu, J., Li, H., Jin, R.: Softtriple loss: deep metric learning without triplet sampling. In: ICCV, pp. 6449\u20136457. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00655"},{"key":"27_CR16","unstructured":"Qian, Q., Xu, Y., Hu, J.: Intra-modal proxy learning for zero-shot visual categorization with clip. In: NeurIPS (2023)"},{"key":"27_CR17","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"issue":"3","key":"27_CR18","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)","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR19","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. In: NeurIPS (2022)"},{"key":"27_CR20","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CoRR abs\/1212.0402 (2012)"},{"key":"27_CR21","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et al.: Robust fine-tuning of zero-shot models. In: CVPR, pp. 7949\u20137961. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"27_CR23","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, pp. 3485\u20133492. IEEE Computer Society (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"27_CR24","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: Tip-adapter: training-free adaption of CLIP for few-shot classification. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13695, pp. 493\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: CVPR, pp. 16795\u201316804. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"27_CR26","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. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."}],"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\/978-3-031-72980-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:25:25Z","timestamp":1730107525000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 October 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"}}]}}