{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:18:01Z","timestamp":1783455481396,"version":"3.55.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"S-Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3683307","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:36:20Z","timestamp":1776108980000},"page":"9486-9501","source":"Crossref","is-referenced-by-count":0,"title":["Text4Seg++: Advancing Image Segmentation via Generative Language Modeling"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3311-0295","authenticated-orcid":false,"given":"Mengcheng","family":"Lan","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6137-5162","authenticated-orcid":false,"given":"Chaofeng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2498-5812","authenticated-orcid":false,"given":"Jiaxing","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4357-9593","authenticated-orcid":false,"given":"Zongrui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9473-3202","authenticated-orcid":false,"given":"Yiping","family":"Ke","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9104-2315","authenticated-orcid":false,"given":"Xudong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7893-0764","authenticated-orcid":false,"given":"Yingchen","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2661-3169","authenticated-orcid":false,"given":"Yunqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2570-9118","authenticated-orcid":false,"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref3","article-title":"Deepseek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref5","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4077"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref12","first-page":"60116","article-title":"NExT-Chat: An LMM for chat, detection and segmentation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3434373"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2235"},{"key":"ref25","article-title":"Text4Seg: Reimagining image segmentation as text generation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Lan","year":"2025"},{"key":"ref26","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref27","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref28","article-title":"Deepseek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref29","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref31","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref32","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.52202\/075280-2142","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref34","first-page":"13040","article-title":"mPLUG-Owl2: Revolutionizing multi-modal large language model with modality collaboration","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Ye","year":"2024"},{"issue":"8","key":"ref35","article-title":"LLaVA-NEXT: Improved reasoning, OCR, and world knowledge, january 2024","volume":"1","author":"Liu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref37","article-title":"LLaVA-onevision: Easy visual task transfer","volume-title":"Trans. Mach. Learn. Res.","author":"Li","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3637265"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref40","first-page":"36","article-title":"SPHINX: A mixer of weights, visual embeddings and image scales for multi-modal large language models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lin","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01878"},{"key":"ref42","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref43","article-title":"Qwen2. 5-VL technical report","author":"Bai","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref45","article-title":"MMR: A large-scale benchmark dataset for multi-target and multi-granularity reasoning segmentation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Jang","year":"2025"},{"key":"ref46","article-title":"SegLLM: Multi-round reasoning segmentation with large language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Wang","year":"2025"},{"key":"ref47","article-title":"Segearth-r1: Geospatial pixel reasoning via large language model","author":"Li","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2025.3560293"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1163\/2405-8262_rgg4_sim_125206"},{"key":"ref50","article-title":"Pixel-sail: Single transformer for pixel-grounded understanding","author":"Zhang","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02160"},{"key":"ref52","article-title":"ALTo: Adaptive-length tokenizer for autoregressive mask generation","author":"Wang","year":"2025"},{"key":"ref53","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref56","article-title":"Grounding multimodal large language models to the world","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Peng","year":"2024"},{"key":"ref57","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1823"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref61","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref62","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1966.1053907"},{"key":"ref65","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref66","article-title":"SAMRefiner: Taming segment anything model for universal mask refinement","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Lin","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35383"},{"key":"ref68","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3468640"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00349"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02814"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02517"},{"key":"ref79","article-title":"Seg-Zero: Reasoning-chain guided segmentation via cognitive reinforcement","author":"Liu","year":"2025"},{"key":"ref80","article-title":"GeoGround: A unified large vision-language model. for remote sensing visual grounding","author":"Zhou","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11479916.pdf?arnumber=11479916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:49Z","timestamp":1783453489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11479916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":80,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3683307","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}