{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:35Z","timestamp":1777888895074,"version":"3.51.4"},"reference-count":91,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB2808903"],"award-info":[{"award-number":["2024YFB2808903"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.02057","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22153-22164","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Visual Large Language Model for Multi-Granular Versatile Perception"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Xiang","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxian","family":"Tan","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengjie","family":"Li","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref5","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref11","volume-title":"Openvocabulary universal image segmentation with maskclip","author":"Ding","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01339"},{"key":"ref16","volume-title":"Video-r1: Reinforcing video reasoning in mllms","author":"Feng","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3361"},{"key":"ref18","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2943"},{"key":"ref20","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1007\/978-3-031-73010-8_23","article-title":"Llava-uhd: An 1 mm perceiving any aspect ratio and highresolution images","volume-title":"Computer Vision-ECCV 2024","author":"Guo","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32380"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref30","article-title":"A spoken language dataset of descriptions for speech-based grounded language learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Kebe","year":"2021"},{"key":"ref31","article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2023","journal-title":"ICLR"},{"key":"ref32","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"ArXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02274"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00598"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200416"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref44","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref50","volume-title":"Visualrft: Visual reinforcement fine-tuning","author":"Liu","year":"2025"},{"key":"ref51","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"issue":"Part IV 14","key":"ref54","first-page":"792","article-title":"Modeling context between objects for referring expression understanding","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Varun","year":"2016"},{"issue":"Part IV 14","key":"ref55","first-page":"792","article-title":"Modeling context between objects for referring expression understanding","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Varun","year":"2016"},{"key":"ref56","volume-title":"Vision-aware text features in referring image segmentation: From object understanding to context understanding","author":"Hai","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01236"},{"key":"ref58","article-title":"Pixellm: Pixel reasoning with large multimodal model","author":"Ren","year":"2023","journal-title":"ArXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref62","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref66","article-title":"Ov-dino: Unified open-vocabulary detection with language-aware selective fusion","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref68","article-title":"Time-R1: PostTraining Large Vision Language Model for Temporal Video Grounding","author":"Wang","year":"2025","journal-title":"arXiv e-prints, art. arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01139"},{"key":"ref70","article-title":"Lasagna: Language-based segmentation assistant for complex queries","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00835"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01464"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00370"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01891"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00928"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00181"},{"key":"ref87","article-title":"Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref91","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11445297.pdf?arnumber=11445297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:40Z","timestamp":1777611700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}