{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:28:06Z","timestamp":1779380886941,"version":"3.53.1"},"reference-count":55,"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\/iccv51701.2025.01878","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20193-20203","source":"Crossref","is-referenced-by-count":3,"title":["Instructseg: Unifying Instructed Visual Segmentation with Multi-Modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Cong","family":"Wei","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxian","family":"Tan","sequence":"additional","affiliation":[{"name":"Meituan Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingsen","family":"Zeng","sequence":"additional","affiliation":[{"name":"Meituan Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfa","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","volume-title":"arXiv preprint","author":"Bai","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022"},{"key":"ref4","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic.","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref6","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices.","volume-title":"arXiv preprint","author":"Chu","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"issue":"6","key":"ref9","doi-asserted-by":"crossref","first-page":"7900","DOI":"10.1109\/TPAMI.2022.3217852","volume":"45","author":"Ding","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00106"},{"issue":"2","key":"ref13","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models.","volume-title":"ICLR","volume":"1","author":"Hu","year":"2022"},{"key":"ref14","first-page":"3","article-title":"Phi-2: The surprising power of small language models","volume-title":"Microsoft Research Blog","volume":"1","author":"Javaheripi","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref18","volume-title":"ArXiv, abs\/2308.00692","author":"Lai","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref20","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"arXiv preprint","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref22","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding.","volume-title":"Advances in neural information processing systems","volume":"34","author":"Li","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref25","article-title":"Visual instruction tuning.","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1149"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref33","article-title":"Perceptiongpt: Effectively fusing visual perception into 11 m.","volume-title":"arXiv preprint","author":"Pi","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01236"},{"key":"ref35","article-title":"PixelLM: Pixel reasoning with large multimodal model.","volume-title":"ArXiv, abs\/2312.02228","author":"Ren","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref37","article-title":"Trackgpt-a generative pre-trained transformer for cross-domain entity trajectory forecasting.","volume-title":"arXiv preprint","author":"Stroh","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01139"},{"key":"ref40","article-title":"Lasagna: Language-based segmentation assistant for complex queries.","volume-title":"arXiv preprint","author":"Wei","year":"2024"},{"key":"ref41","article-title":"Hyperseg: Towards universal visual segmentation with large language model.","volume-title":"arXiv preprint","author":"Wei","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00370"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref49","article-title":"Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding","volume-title":"arXiv preprint","author":"Zhang","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1071"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref52","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"arXiv preprint","author":"Zhu","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33194"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref55","article-title":"Segment everything everywhere all at once.","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zou","year":"2024"}],"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\/11443454.pdf?arnumber=11443454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:32:38Z","timestamp":1777530758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01878","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}