{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:07:57Z","timestamp":1779739677169,"version":"3.53.1"},"reference-count":72,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406053"],"award-info":[{"award-number":["62406053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441231"],"award-info":[{"award-number":["62441231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liaoning Provincial Doctoral Scientific Research Start-Up Fund Project","award":["2025-BS-0080"],"award-info":[{"award-number":["2025-BS-0080"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT25LAB128"],"award-info":[{"award-number":["DUT25LAB128"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dalian Municipal Science and Technology Talent Innovation Support Program","award":["2025RQ24"],"award-info":[{"award-number":["2025RQ24"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3689427","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:43:00Z","timestamp":1778096580000},"page":"5239-5252","source":"Crossref","is-referenced-by-count":0,"title":["Context-Infused Trajectories: Enhancing Context and Frame Consistency in Reasoning Video Object Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8661-1093","authenticated-orcid":false,"given":"Sitong","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-4437","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9245-5544","authenticated-orcid":false,"given":"Qi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7463-6103","authenticated-orcid":false,"given":"Wenda","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref3","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3522802"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref9","article-title":"ViLLa: Video reasoning segmentation with large language model","author":"Zheng","year":"2024","journal-title":"arXiv:2407.14500"},{"key":"ref10","article-title":"Tracking meets large multimodal models for driving scenario understanding","author":"Ishaq","year":"2025","journal-title":"arXiv:2503.14498"},{"key":"ref11","article-title":"Video-of-thought: Step-by-step video reasoning from perception to cognition","author":"Fei","year":"2024","journal-title":"arXiv:2501.03230"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3122293"},{"key":"ref13","article-title":"VidEgoThink: Assessing egocentric video understanding capabilities for embodied AI","author":"Cheng","year":"2024","journal-title":"arXiv:2410.11623"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755703"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref19","article-title":"LVOS: A benchmark for large-scale long-term video object segmentation","author":"Hong","year":"2024","journal-title":"arXiv:2404.19326"},{"key":"ref20","volume-title":"Sam 2: Segment Anything in Images and Videos","author":"Ravi et al","year":"2025"},{"key":"ref21","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref24","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":"ref25","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref27","first-page":"1","article-title":"Grounding multimodal large language models to the world","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref28","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref29","article-title":"Qwen2-VL: Enhancing vision-language Model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref30","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","volume-title":"LLaVA","author":"Liu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref34","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00318"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01282"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref40","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Yang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3383592"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137660"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327588"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3208409"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00374"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01520"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00511"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3418980"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00365"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1149"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00835"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref61","volume-title":"Llava++: Extending Visual Capabilities With Llama-3 and Phi-3","author":"Rasheed","year":"2024"},{"key":"ref62","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01878"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11511402.pdf?arnumber=11511402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:56:44Z","timestamp":1779739004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11511402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3689427","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}