{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:14:43Z","timestamp":1783131283038,"version":"3.54.6"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council, Taiwan","doi-asserted-by":"publisher","award":["NSTC 112-2221-E-002-182-MY3"],"award-info":[{"award-number":["NSTC 112-2221-E-002-182-MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council, Taiwan","doi-asserted-by":"publisher","award":["112-2221-E-002-132-MY3"],"award-info":[{"award-number":["112-2221-E-002-132-MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006477","name":"National Taiwan University","doi-asserted-by":"publisher","award":["114L900902"],"award-info":[{"award-number":["114L900902"]}],"id":[{"id":"10.13039\/501100006477","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tce.2025.3650288","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:49:41Z","timestamp":1768596581000},"page":"283-290","source":"Crossref","is-referenced-by-count":1,"title":["MAViS: A Multi-Agent Approach for Training-Free Referring Video Object Segmentation"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1850-929X","authenticated-orcid":false,"given":"Tai","family":"Peng","sequence":"first","affiliation":[{"name":"Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2959-2471","authenticated-orcid":false,"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3391743"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3319498"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3419119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref12","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32387"},{"key":"ref15","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235720"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref29","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. (ICML)","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref31","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref32","first-page":"61501","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref34","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref35","article-title":"Seed1.5-VL technical report","volume-title":"arXiv:2505.07062","author":"Guo","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref39","article-title":"VideoMultiAgents: A multi-agent framework for video question answering","author":"Kugo","year":"2025","journal-title":"arXiv:2504.20091"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.559"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref45","first-page":"26425","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Luo"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_26"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref49","first-page":"20193","article-title":"InstructSeg: Unifying instructed visual segmentation with multi-modal large language models","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Wei"},{"key":"ref50","article-title":"ReferDINO: Referring video object segmentation with visual grounding foundations","author":"Liang","year":"2025","journal-title":"arXiv:2501.14607"},{"key":"ref51","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":"ref52","article-title":"Learning referring video object segmentation from weak annotation","author":"Zhao","year":"2023","journal-title":"arXiv:2308.02162"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"ref54","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dao"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11456295\/11355800.pdf?arnumber=11355800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:51:38Z","timestamp":1774554698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3650288","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}