{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:24Z","timestamp":1792786944439,"version":"4.5.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62227807"],"award-info":[{"award-number":["62227807"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Supercomputing Center of Lanzhou University","id":[{"id":"https:\/\/ror.org\/01mkqqe32","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3696843","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:53:59Z","timestamp":1779738839000},"page":"11822-11837","source":"Crossref","is-referenced-by-count":1,"title":["Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5378-6225","authenticated-orcid":false,"given":"Jisheng","family":"Dang","sequence":"first","affiliation":[{"name":"Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Hong Kong","department":["Department of Data and Systems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3614-1027","authenticated-orcid":false,"given":"Haowen","family":"Yan","sequence":"additional","affiliation":[{"name":"Lanzhou Jiaotong University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6729-4176","authenticated-orcid":false,"given":"Huicheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3514-5413","authenticated-orcid":false,"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref3","article-title":"LLaVA-interactive: An all-in-one demo for image chat, segmentation, generation and editing","author":"Chen","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","article-title":"Xtuner: A toolkit for efficiently fine-tuning LLM","volume-title":"GitHub repository","year":"2023"},{"key":"ref7","article-title":"Towards multi-path agentic reasoning for grounded video question answering","author":"Dang","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-37577-3_34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3680029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref11","article-title":"Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4899"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref16","first-page":"14271","article-title":"VTimeLM: Empower LLM to grasp video moments","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Huang"},{"key":"ref17","first-page":"1177","article-title":"Reason 3D: Searching and reasoning 3D segmentation via large language model","volume-title":"Proc. Int. Conf. 3D Vis.","author":"Huang"},{"key":"ref18","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hwang"},{"key":"ref21","first-page":"13700","article-title":"Chat-UniVi: Unified visual representation empowers large language models with image and video understanding","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Peng"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref26","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref27","article-title":"Seed-bench: Benchmarking multimodal LLMs with generative comprehension","author":"Li","year":"2023"},{"key":"ref28","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"},{"key":"ref29","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref30","first-page":"13923","article-title":"Tube-link: A flexible cross tube baseline for universal video segmentation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref32","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023"},{"key":"ref33","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382308"},{"key":"ref35","first-page":"126","article-title":"LLaVA-plus: Learning to use tools for creating multimodal agents","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Liu"},{"key":"ref36","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref37","article-title":"Generalizable entity grounding via assistance of large language model","author":"Lu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref40","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref45","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref46","article-title":"LaSagnA: Language-based segmentation assistant for complex queries","author":"Wei","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref49","article-title":"VISA: Reasoning video object segmentation via large language models","author":"Yan","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3468640"},{"key":"ref51","article-title":"mPLUG-Owl3: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3720379"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3562930"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3368112"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_30"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11535029.pdf?arnumber=11535029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:20:59Z","timestamp":1790270459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11535029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":58,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3696843","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":[[2026,10]]}}}