{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:26:11Z","timestamp":1780053971670,"version":"3.54.0"},"reference-count":41,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276108"],"award-info":[{"award-number":["62276108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02145","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23105-23114","source":"Crossref","is-referenced-by-count":1,"title":["GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding"],"prefix":"10.1109","author":[{"given":"Rui","family":"Hu","sequence":"first","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianghui","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianheng","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[{"name":"vivo AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Liu","sequence":"additional","affiliation":[{"name":"vivo AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longjin","family":"Ran","sequence":"additional","affiliation":[{"name":"vivo AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxin","family":"Chen","sequence":"additional","affiliation":[{"name":"vivo AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Claude 3.7 sonnet system card"},{"key":"ref2","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Coco-stuff: Thing and stuff classes in context","volume":"abs\/1612.03716","author":"Caesar","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref7","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref18","year":"2024","journal-title":"Mistral-small-3.1\u201324b-instruct-2503"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref23","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref25","article-title":"Seed1.5-vl technical report","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","volume-title":"Doubao-1.5-pro","year":"2024"},{"key":"ref27","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01235"},{"key":"ref29","article-title":"Instructseg: Unifying instructed visual segmentation with multi-modal large language models","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref33","first-page":"18155","article-title":"Torr","volume-title":"Lavt: Language-aware vision transformer for referring image segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Yang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102091"},{"key":"ref35","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref37","article-title":"Evf-sam: Early vision-language fusion for text-prompted segment anything model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"74","article-title":"Psalm: Pixelwise segmentation with large multi-modal model","volume-title":"European Conference on Computer Vision","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref41","article-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv preprint"}],"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\/11443372.pdf?arnumber=11443372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:46Z","timestamp":1777612486000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02145","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}