{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:57:09Z","timestamp":1781157429751,"version":"3.54.1"},"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:\/\/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":["62472104"],"award-info":[{"award-number":["62472104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xiaomi Young Scholars Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3697653","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:09:12Z","timestamp":1780430952000},"page":"6055-6067","source":"Crossref","is-referenced-by-count":0,"title":["Event-Aware Instructed Assistant for Referring Video Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6658-1175","authenticated-orcid":false,"given":"Jinyu","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref5","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv:2312.14238"},{"key":"ref6","first-page":"18378","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195188370.001.0001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.4324\/9781315009292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60422-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"ref22","article-title":"Reinforcing video reasoning segmentation to think before it segments","author":"Gong","year":"2025","journal-title":"arXiv:2508.11538"},{"key":"ref23","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv:2402.03300"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref29","first-page":"542","article-title":"Referring expression object segmentation with caption-aware consistency","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref36","article-title":"DualFocus: Integrating macro and micro perspectives in multi-modal large language models","author":"Cao","year":"2024","journal-title":"arXiv:2402.14767"},{"key":"ref37","article-title":"Qwen-VL: A frontier large vision-language model w ith versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref41","first-page":"12","article-title":"Image as set of points","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref42","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Rao"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref47","first-page":"1132","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref48","first-page":"52","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"van den Oord"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref51","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref53","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref54","first-page":"101","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1149"},{"key":"ref62","article-title":"Tracking with human-intent reasoning","author":"Zhu","year":"2023","journal-title":"arXiv:2312.17448"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"},{"key":"ref66","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11547898.pdf?arnumber=11547898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:02:58Z","timestamp":1781154178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11547898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3697653","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}