{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:30:37Z","timestamp":1778661037500,"version":"3.51.4"},"reference-count":85,"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\/iccv51701.2025.02012","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21667-21678","source":"Crossref","is-referenced-by-count":1,"title":["Referring to Any Person"],"prefix":"10.1109","author":[{"given":"Qing","family":"Jiang","sequence":"first","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Wu","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhe","family":"Ren","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuda","family":"Xiong","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Qin","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen2","author":"Bai","year":"2025","journal-title":"5-vl technical report. arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref5","volume-title":"Coyo- 700 m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref6","article-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model","author":"Hardy Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00056"},{"key":"ref9","article-title":"Shikra: Unleashing multimodal 11 m \u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01445"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref14","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref20","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01114"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","article-title":"Chatrex: Taming multimodal 11 m for joint perception and understanding","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","article-title":"Aria: An open multimodal native mixture-ofexperts model","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref35","article-title":"Eagle 2: Building posttraining data strategies from scratch for frontier vision-language models","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00390"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref46","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref53","volume-title":"Gpt-4v(ision) system card","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547765"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref59","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Dino-x: A unified vision model for openworld object detection and understanding","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Grounding dino 1","author":"Ren","year":"2024","journal-title":"5: Advance the \u201cedge\u201d of open-set object detection. arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2771"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref66","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01464"},{"key":"ref70","article-title":"Deepseek-vl 2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Qwen2","author":"Yang","year":"2024","journal-title":"5 technical report. arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref74","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","first-page":"69","article-title":"Berg. Modeling context in referring expressions","author":"Yu","year":"2016","journal-title":"ECCV"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01276"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref79","article-title":"Griffon v2: Advancing multimodal perception with high-resolution scaling and visual-language co-referring","author":"Zhan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_23"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351063"},{"key":"ref82","article-title":"Mm1","author":"Zhang","year":"2024","journal-title":"5: Methods, analysis & insights from multimodal 11 m fine-tuning. arXiv preprint"},{"key":"ref83","article-title":"Ferretv 2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00783"}],"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\/11445540.pdf?arnumber=11445540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:37Z","timestamp":1777529917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02012","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}