{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T18:34:26Z","timestamp":1754159666143,"version":"3.41.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849818","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:36:57Z","timestamp":1737985017000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["IoU-CLIP: IoU-Aware Language-Image Model Tuning for Open Vocabulary Object Detection"],"prefix":"10.1109","author":[{"given":"Mingzhou","family":"He","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"King Ngi","family":"Ngan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"Yiming","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"Fanman","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"Heqian","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China,611731"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref2","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01171"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref8","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"journal-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","year":"2022","author":"Kuo","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"journal-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref20","first-page":"33 781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume":"35","author":"Bangalath","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"journal-title":"Learning object-language alignments for open-vocabulary object detection","year":"2022","author":"Lin","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01650"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01578"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2024,12,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,12,11]]}},"container-title":["2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10849624\/10849781\/10849818.pdf?arnumber=10849818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T17:51:25Z","timestamp":1753465885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849818","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}