{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:31:21Z","timestamp":1780057881586,"version":"3.54.0"},"reference-count":66,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00055","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"508-518","source":"Crossref","is-referenced-by-count":1,"title":["UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Zhang","sequence":"first","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wei","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenda","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyi","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangxiang","family":"Chu","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00545"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27853"},{"key":"ref7","article-title":"Pali: A jointlyscaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02227"},{"key":"ref9","article-title":"Gpg: A simple and strong reinforcement learning baseline for model reasoning","author":"Chu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01204"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01707"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3641542"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3014013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00250"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093358"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref24","article-title":"Driving in the matrix: Can virtual worlds replace humangenerated annotations for real world tasks?","author":"Johnson-Roberson","year":"2016","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3061204"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28076"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00436"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01667"},{"key":"ref30","article-title":"Learning domain-aware detection head with prompt tuning","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3289"},{"key":"ref32","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3370978"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01069"},{"key":"ref36","article-title":"Next token is enough: Realistic image quality and aesthetic scoring with multimodal large language model","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02724"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00744"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00050"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01268"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02697"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217046"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_47"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3480120"},{"key":"ref46","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems, 28"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00470"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00347"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_20"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088859"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3084354"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671721"},{"key":"ref56","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International conference on machine learning","author":"Wang","year":"2022"},{"key":"ref57","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00092"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28410"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29540"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02209"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref64","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01584"}],"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\/11446121.pdf?arnumber=11446121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:21Z","timestamp":1777530141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00055","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}