{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:42Z","timestamp":1778048502249,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00550","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5672-5681","source":"Crossref","is-referenced-by-count":0,"title":["Grounding Descriptions in Images informs Zero-Shot Visual Recognition"],"prefix":"10.1109","author":[{"given":"Shaunak","family":"Halbe","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjiao","family":"Tian","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K J","family":"Joseph","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Seale Smith","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katherine","family":"Stevo","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineeth N","family":"Balasubramanian","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zsolt","family":"Kira","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bica","year":"2024","journal-title":"Improving fine-grained understanding in image-text pre-training"},{"key":"ref2","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1337"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01108"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref11","author":"Jia","year":"2021","journal-title":"Scaling up visual and vision-language representation learning with noisy text supervision"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref13","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref15","author":"Maji","year":"2013","journal-title":"Fine-grained visual classification of aircraft"},{"key":"ref16","article-title":"Visual classification via description from large language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Menon"},{"key":"ref17","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref21","author":"Radford","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref26","author":"den Oord","year":"2019","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","volume-title":"Cub. Technical Report CNS-TR-2011-001","author":"Wah","year":"2011"},{"key":"ref29","author":"Wolf","year":"2020","journal-title":"Hugging-face\u2019s transformers: State-of-the-art natural language processing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00402"},{"key":"ref31","author":"Yao","year":"2021","journal-title":"Filip: Fine-grained interactive language-image pre-training"},{"key":"ref32","author":"Yuksekgonul","year":"2023","journal-title":"When and why vision-language models behave like bags-of-words, and what to do about it?"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref34","author":"Zhang","year":"2024","journal-title":"Why are visually-grounded language models bad at image classification?"},{"key":"ref35","author":"Zhao","year":"2025","journal-title":"Grad-eclip: Gradient-based visual and textual explanations for clip"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492542.pdf?arnumber=11492542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:22Z","timestamp":1778047642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00550","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}