{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:10:48Z","timestamp":1771953048496,"version":"3.50.1"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_7","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:17:40Z","timestamp":1733289460000},"page":"107-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Prompting Language-Informed Distribution for\u00a0Compositional Zero-Shot Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2571-3341","authenticated-orcid":false,"given":"Wentao","family":"Bao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1384-2760","authenticated-orcid":false,"given":"Lichang","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3483-8333","authenticated-orcid":false,"given":"Heng","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6271-4082","authenticated-orcid":false,"given":"Yu","family":"Kong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"7_CR1","first-page":"1462","volume":"33","author":"Y Atzmon","year":"2020","unstructured":"Atzmon, Y., Kreuk, F., Shalit, U., Chechik, G.: A causal view of compositional zero-shot recognition. Adv. Neural Inform. Process. Syst. 33, 1462\u20131473 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bang, D., et al.: Logit mixing training for more reliable and accurate prediction. In: IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/390"},{"key":"7_CR3","unstructured":"Carratino, L., Ciss\u00c3c, M., Jenatton, R., Vert, J.P.: On mixup regularization. JMLR 23(325) (2022)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Derakhshani, M.M., et al.: Bayesian prompt learning for image-language model generalization. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01398"},{"key":"7_CR5","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: ICLR (2023)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Huang, S., Gong, B., Feng, Y., Lv, Y., Wang, D.: Troika: multi-path cross-modal traction for compositional zero-shot learning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02266"},{"key":"7_CR7","unstructured":"Huynh, D., Elhamifar, E.: Compositional zero-shot learning via fine-grained dense feature composition. Adv. Neural Inform. Process. Syst. (2020)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Isola, P., Lim, J.J., Adelson, E.H.: Discovering states and transformations in image collections. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"7_CR9","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Karthik, S., Mancini, M., Akata, Z.: Kg-sp: knowledge guided simple primitives for open world compositional zero-shot learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kwon, H., Song, T., Jeong, S., Kim, J., Jang, J., Sohn, K.: Probabilistic prompt learning for dense prediction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00654"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40 (2017)","DOI":"10.1017\/S0140525X16001837"},{"key":"7_CR14","unstructured":"Lewis, M., Yu, Q., Merullo, J., Pavlick, E.: Does clip bind concepts? probing compositionality in large image models. arXiv preprint arXiv:2212.10537 (2022)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Wei, K., Deng, C., Yang, M.: Siamese contrastive embedding network for compositional zero-shot learning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y.L., Xu, Y., Mao, X., Lu, C.: Symmetry and group in attribute-object compositions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01133"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, Z., Chen, H., Yao, L.: Context-based and diversity-driven specificity in compositional zero-shot learning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"7_CR18","unstructured":"Liu, X., et al.: Patch-token aligned bayesian prompt learning for vision-language models. arXiv preprint arXiv:2303.09100 (2023)"},{"key":"7_CR19","unstructured":"Liu, Z., et al.: Simple primitives with feasibility-and contextuality-dependence for open-world compositional zero-shot learning. arXiv preprint arXiv:2211.02895 (2022)"},{"key":"7_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Lu, X., Liu, Z., Guo, S., Guo, J.: Decomposed soft prompt guided fusion enhancing for compositional zero-shot learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02256"},{"key":"7_CR22","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":"7_CR23","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: Crepe: can vision-language foundation models reason compositionally? In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Maniparambil, M., Vorster, C., Molloy, D., Murphy, N., McGuinness, K., O\u2019Connor, N.E.: Enhancing clip with gpt-4: harnessing visual descriptions as prompts. arXiv preprint arXiv:2307.11661 (2023)","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"7_CR26","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: ICLR (2023)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Misra, I., Gupta, A., Hebert, M.: From red wine to red tomato: composition with context. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.129"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., Akata, Z.: Learning graph embeddings for compositional zero-shot learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Grauman, K.: Attributes as operators: factorizing unseen attribute-object compositions. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"7_CR30","unstructured":"Nayak, N.V., Yu, P., Bach, S.H.: Learning to compose soft prompts for compositional zero-shot learning. In: ICLR (2023)"},{"key":"7_CR31","unstructured":"OpenAI: OpenAI GPT-3.5 API [gpt-3.5-turbo-0125]. https:\/\/openai.com\/blog\/chatgpt. Accessed 2023"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Purushwalkam, S., Nickel, M., Gupta, A., Ranzato, M.: Task-driven modular networks for zero-shot compositional learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00369"},{"key":"7_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"issue":"1","key":"7_CR35","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21(1), 5485\u20135551 (2020)","journal-title":"JMLR"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Razdaibiedina, A., et al.: Residual prompt tuning: improving prompt tuning with residual reparameterization. In: ACL (2023)","DOI":"10.18653\/v1\/2023.findings-acl.421"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Wang, Y.X., Hebert, M.: Learning compositional representations for few-shot recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00647"},{"key":"7_CR38","unstructured":"Trager, M., et al.: Linear spaces of meanings: the compositional language of vlms. arXiv preprint arXiv:2302.14383 (2023)"},{"key":"7_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. (2017)"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Yang, M., Wei, K., Deng, C.: Hierarchical prompt learning for compositional zero-shot recognition. In: IJCAI (2023)","DOI":"10.24963\/ijcai.2023\/163"},{"key":"7_CR41","unstructured":"Wolff, M., Brendel, W., Wolff, S.: The independent compositional subspace hypothesis for the structure of clip\u2019s last layer. In: ICLR Workshop (2023)"},{"key":"7_CR42","unstructured":"Xu, G., Kordjamshidi, P., Chai, J.: Prompting large pre-trained vision-language models for compositional concept learning. arXiv preprint arXiv:2211.05077 (2022)"},{"key":"7_CR43","unstructured":"Yan, A., et al.: Learning concise and descriptive attributes for visual recognition. arXiv preprint arXiv:2308.03685 (2023)"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Yu, A., Grauman, K.: Fine-grained visual comparisons with local learning. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.32"},{"key":"7_CR45","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: ICLR (2023)"},{"key":"7_CR46","unstructured":"Zhang, S., et\u00a0al.: Opt: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, T., Liang, K., Du, R., Sun, X., Ma, Z., Guo, J.: Learning invariant visual representations for compositional zero-shot learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_20"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zhu, H., Nevatia, R.: Caila: concept-aware intra-layer adapters for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1721\u20131731 (2024)","DOI":"10.1109\/WACV57701.2024.00174"},{"key":"7_CR49","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"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. IJCV (2022)","DOI":"10.1007\/s11263-022-01653-1"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Zou, Y., Zhang, S., Chen, K., Tian, Y., Wang, Y., Moura, J.M.: Compositional few-shot recognition with primitive discovery and enhancing. In: ACM MM (2020)","DOI":"10.1145\/3394171.3413849"}],"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\/978-3-031-72630-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:38:09Z","timestamp":1768199889000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}