{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:46Z","timestamp":1777888726853,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-23-1-2780"],"award-info":[{"award-number":["N00014-23-1-2780"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017567","name":"Apple","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00157","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1602-1612","source":"Crossref","is-referenced-by-count":0,"title":["Verbalized Representation Learning for Interpretable Few-Shot Generalization"],"prefix":"10.1109","author":[{"given":"Cheng-Fu","family":"Yang","sequence":"first","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Yin","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Ji","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanyun","family":"Peng","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3425"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref6","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"This looks like that: deep learning for interpretable image recognition","author":"Chen","year":"2019","journal-title":"Advances in neural information processing systems, 32"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref11","article-title":"Solo: A single transformer for scalable vision-language modeling","author":"Chen","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016309"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref16","article-title":"Learning visual attributes","author":"Ferrari","year":"2007","journal-title":"Advances in neural information processing systems, 20"},{"key":"ref17","article-title":"Devise: A deep visual-semantic embedding model","author":"Frome","year":"2013","journal-title":"Advances in neural information processing systems, 26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_17"},{"key":"ref21","article-title":"Natural language descriptions of deep visual features","volume-title":"International Conference on Learning Representations","author":"Hernandez","year":"2021"},{"key":"ref22","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.132"},{"key":"ref24","article-title":"Visualizing and understanding recurrent networks","author":"Karpathy","year":"2015","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"5338","article-title":"Concept bottleneck models","volume-title":"International conference on machine learning","author":"Koh","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref28","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32576"},{"key":"ref31","article-title":"Envisioning class entity reasoning by large language models for few-shot learning","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-65455-6"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref35","volume-title":"ChatGPT","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"12","key":"ref40","first-page":"3","article-title":"Synaesthesia-a window into perception, thought and language","volume":"8","author":"Ramachandran","year":"2001","journal-title":"Journal of consciousness studies"},{"key":"ref41","article-title":"Optimization as a model for few-shot learning","volume-title":"International conference on learning representations","author":"Ravi","year":"2017"},{"key":"ref42","first-page":"2152","article-title":"An embarrassingly simple approach to zero-shot learning","volume-title":"International conference on machine learning","author":"Romera-Paredes","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","article-title":"A multimodal automated interpretability agent","volume-title":"Forty-first International Conference on Machine Learning","author":"Shaham","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01049"},{"key":"ref46","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00287"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0470"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref51","article-title":"Post-hoc concept bottleneck models","author":"Yuksekgonul","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref53","article-title":"Sglang: Efficient execution of structured language model programs","author":"Zheng","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445291.pdf?arnumber=11445291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:45Z","timestamp":1777611345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00157","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}