{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:54Z","timestamp":1777889694927,"version":"3.51.4"},"reference-count":56,"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":["62276260,62472423"],"award-info":[{"award-number":["62276260,62472423"]}],"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\/iccv51701.2025.02130","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22947-22957","source":"Crossref","is-referenced-by-count":0,"title":["Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring"],"prefix":"10.1109","author":[{"given":"Yufei","family":"Zhan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shurong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yousong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref13","article-title":"Pali-3 vision language models: Smaller, faster, stronger","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","author":"Chen","year":"2025","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"T-rex: Counting by visual prompting","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"81461","article-title":"Lumen: Unleashing versatile vision-centric capabilities of large multimodal models","volume":"37","author":"Jiao","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref23","article-title":"Otterhd: A high-resolution multimodality model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0063"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref30","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref31","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"ref36","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Bryan","year":"2015"},{"key":"ref38","article-title":"Cogcom: Train large vision-language models diving into details through chain of manipulations","author":"Qi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref41","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":"ref42","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"ref46","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Grit: A generative region-to-text transformer for object understanding","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174072"},{"key":"ref49","article-title":"Auto-gpt for online decision making: Benchmarks and additional opinions","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref55","article-title":"Bubogpt: Enabling visual grounding in multi-modal llms","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","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\/11445763.pdf?arnumber=11445763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:52Z","timestamp":1777612612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02130","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}