{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:59:10Z","timestamp":1785787150937,"version":"3.56.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"crossref","award":["LQN26F020015"],"award-info":[{"award-number":["LQN26F020015"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23A20326"],"award-info":[{"award-number":["U23A20326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"crossref","award":["2025C01064"],"award-info":[{"award-number":["2025C01064"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3714842","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:02:30Z","timestamp":1784919750000},"page":"8206-8218","source":"Crossref","is-referenced-by-count":0,"title":["Toward Reasoning-Centric Video Object Segmentation via Multi-Modal Large Language Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2708-8474","authenticated-orcid":false,"given":"Yanyan","family":"Shao","sequence":"first","affiliation":[{"name":"Zhejiang Wanli University","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5684","authenticated-orcid":false,"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengze","family":"Zhou","sequence":"additional","affiliation":[{"name":"Adelaide University","place":["Adelaide, SA, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2945-8344","authenticated-orcid":false,"given":"Xiufang","family":"Shi","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-3145","authenticated-orcid":false,"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"Adelaide University","place":["Adelaide, SA, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref8","article-title":"Tracking with human-intent reasoning","author":"Zhu","year":"2023","journal-title":"arXiv:2312.17448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref10","article-title":"Sa2VA: Marrying SAM2 with LLaVA for dense grounded understanding of images and videos","author":"Yuan","year":"2025","journal-title":"arXiv:2501.04001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185487"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2985868"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113791"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3243525"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3161832"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_26"},{"key":"ref29","article-title":"ViLLa: Video reasoning segmentation with large language model","author":"Zheng","year":"2024","journal-title":"arXiv:2407.14500"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"ref31","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref33","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref34","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":"ref35","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0891"},{"key":"ref40","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref41","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref43","article-title":"Kosmos-2: Grounding multimodal large language models to the world","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref44","article-title":"InternGPT: Solving vision-centric tasks by interacting with ChatGPT beyond language","author":"Liu","year":"2023","journal-title":"arXiv:2305.05662"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref48","volume-title":"LLaVA++: Extending Visual Capabilities With LLaVA-3 and Phi-3","author":"Rasheed","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref50","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"issue":"1","key":"ref51","first-page":"83","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"Harold","year":"1995","journal-title":"Naval Res. Logistics Quart."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref59","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3103"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref62","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Malinowski"},{"key":"ref63","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref64","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11623417.pdf?arnumber=11623417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:04:22Z","timestamp":1785783862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11623417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3714842","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}