{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:53:49Z","timestamp":1784300029891,"version":"3.55.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-3-031-72627-9_21","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"370-387","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Meta-prompting for\u00a0Automating Zero-Shot Visual Recognition with\u00a0LLMs"],"prefix":"10.1007","author":[{"given":"M. Jehanzeb","family":"Mirza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonid","family":"Karlinsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sivan","family":"Doveh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Micorek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateusz","family":"Kozinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Horst","family":"Possegger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Proceedings of ECCV (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"21_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv:2005.14165 (2020)"},{"key":"21_CR3","unstructured":"Chen, J., Li, D.Z.X.S.X., Zhang, Z.L.P., Xiong, R.K.V.C.Y., Elhoseiny, M.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: Improving in-context few-shot learning via self-supervised training. arXiv preprint arXiv:2205.01703 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.260"},{"issue":"10","key":"21_CR5","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","volume":"105","author":"G Cheng","year":"2017","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105(10), 1865\u20131883 (2017)","journal-title":"Proc. IEEE"},{"key":"21_CR6","unstructured":"Chiang, W.L., et al.: Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality (March 2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., , Vedaldi, A.: Describing textures in the wild. In: Proceedings of CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"21_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21_CR10","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: Proceedings of CVPR (2004)"},{"key":"21_CR11","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. In: Proceedings of IGARSS (2018)","DOI":"10.1109\/IGARSS.2018.8519248"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"21_CR13","unstructured":"Hou, Y., Dong, H., Wang, X., Li, B., Che, W.: MetaPrompting: learning to Learn Better Prompts. arXiv preprint arXiv:2209.11486 (2022)"},{"key":"21_CR14","unstructured":"Huang, T., Chu, J., Wei, F.: Unsupervised Prompt Learning for Vision-Language Models. arXiv:2204.03649 (2022)"},{"key":"21_CR15","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of ICML (2021)"},{"key":"21_CR16","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral of Experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"21_CR17","unstructured":"Kay, W., et al.: The Kinetics Human Action Video Dataset (2017)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. In: Proceedings of CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"21_CR19","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. NeurIPS 35, 22199\u201322213 (2022)","journal-title":"NeurIPS"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of ICCVW (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"21_CR21","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning Multiple Layers of Features from Tiny Images. Department of Computer Science, University of Toronto, Tech. rep. (2009)"},{"key":"21_CR22","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Lin, W., et al.: MAtch, eXpand and improve: unsupervised finetuning for zero-shot action recognition with language knowledge. In: Proceeidngs of ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved Baselines with Visual Instruction Tuning. arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"21_CR25","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: LLaVA-Next (LLaVA 1.6). arXiv:2310.03744 (2023). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"21_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"21_CR27","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-Grained Visual Classification of Aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"21_CR28","volume-title":"Visual Classification via Description from Large Language Models","author":"S Menon","year":"2023","unstructured":"Menon, S., Vondrick, C.: Visual Classification via Description from Large Language Models. Proc, ICLR (2023)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Min, S., Lewis, M., Zettlemoyer, L., Hajishirzi, H.: MetaICL: Learning to Learn In Context. arXiv preprint arXiv:2110.15943 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"21_CR30","unstructured":"Mirza, M.J., Karlinsky, L., Lin, W., Possegger, H., Feris, R., Bischof, H.: TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification. arXiv preprint arXiv:2309.06809 (2023)"},{"key":"21_CR31","unstructured":"Mirza, M.J., et al.: LaFTer: label-free tuning of zero-shot classifier using language and unlabeled image collections. In: NeurIPS (2023)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of ICVGIP (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"21_CR33","doi-asserted-by":"publisher","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: Proceedings of CVPR, pp. 3498\u20133505 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248092","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"21_CR34","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. arXiv:2209.03320 (2022)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"21_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of ICML (2021)"},{"key":"21_CR36","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: Proceedings of ICML, pp. 5389\u20135400. PMLR (2019)"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Roth, K., Kim, J.M., Koepke, A., Vinyals, O., Schmid, C., Akata, Z.: Waffling around for Performance: Visual Classification with Random Words and Broad Concepts. arXiv preprint arXiv:2306.07282 (2023)","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"21_CR38","unstructured":"Schuhmann, C., et al.: LAION-5b: an open large-scale dataset for training next generation image-text models. In: NeurIPS (2022)"},{"key":"21_CR39","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. arXiv:1212.0402 (2012)"},{"key":"21_CR40","unstructured":"Suzgun, M., Kalai, A.T.: Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding. arXiv preprint arXiv:2401.12954 (2024)"},{"key":"21_CR41","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR42","volume-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"C Wah","year":"2011","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Tech. rep, California Institute of Technology (2011)"},{"key":"21_CR43","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: NeurIPS (2019)"},{"key":"21_CR44","unstructured":"Wei, J., et al.: Finetuned Language Models Are Zero-Shot Learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"21_CR45","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35, 24824\u201324837 (2022)","journal-title":"NeurIPS"},{"key":"21_CR46","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: Proceedings of CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"21_CR47","unstructured":"Xu, H., et al.: Demystifying CLIP data. In: Proceedings of ICLR (2023)"},{"key":"21_CR48","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. In: NeurIPS, vol. 36 (2023)"},{"key":"21_CR49","unstructured":"Zhao, Z., Wallace, E., Feng, S., Klein, D., Singh, S.: Calibrate before use: improving few-shot performance of language models. In: Proceedings of ICML, pp. 12697\u201312706. PMLR (2021)"},{"issue":"6","key":"21_CR50","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.: Places: a 10 million image database for scene recognition. IEEE TPAMI 40(6), 1452\u20131464 (2017)","journal-title":"IEEE TPAMI"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. In: IJCV (2022)","DOI":"10.1007\/s11263-022-01653-1"},{"key":"21_CR53","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592 (2023)"}],"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\/978-3-031-72627-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:07:42Z","timestamp":1729372062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 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"}}]}}