{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:05:41Z","timestamp":1775189141256,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100005289","name":"National Institute of Justice","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,27]]},"DOI":"10.1109\/aipr60534.2023.10440710","type":"proceedings-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T19:19:17Z","timestamp":1708629557000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Exploring CLIP for Real World, Text-based Image Retrieval"],"prefix":"10.1109","author":[{"given":"Manal","family":"Sultan","sequence":"first","affiliation":[{"name":"California Institute of Technology,Computer Science,Pasadena,California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lia","family":"Jacobs","sequence":"additional","affiliation":[{"name":"Ohio State University,Computer Science,Columbus,Ohio"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abby","family":"Stylianou","sequence":"additional","affiliation":[{"name":"Saint Louis University,Computer Science,Saint Louis,Missouri"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Pless","sequence":"additional","affiliation":[{"name":"George Washington University,Computer Science,Washington, DC,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref2","volume-title":"Clip retrieval: Easily compute clip embeddings and build a clip retrieval system with them","author":"Beaumont","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093362"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e16757"},{"key":"ref5","author":"Ilharco","year":"2021","journal-title":"Openclip"},{"key":"ref6","article-title":"Chatting makes perfect: Chat-based image retrieval","author":"Levy","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614156"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref10","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref12","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2015.7444535"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2017.8457947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301726"},{"key":"ref17","article-title":"Parts of speech grounded subspaces in vision language models","volume-title":"Proceedings of the thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)","author":"Tzelepis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534136"}],"event":{"name":"2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)","location":"St. Louis, MO, USA","start":{"date-parts":[[2023,9,27]]},"end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10440654\/10440655\/10440710.pdf?arnumber=10440710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T03:42:18Z","timestamp":1709264538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,27]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/aipr60534.2023.10440710","relation":{},"subject":[],"published":{"date-parts":[[2023,9,27]]}}}