{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:34:01Z","timestamp":1775579641827,"version":"3.50.1"},"reference-count":119,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":"Shanghai Pujiang Programme","award":["24PJD030"],"award-info":[{"award-number":["24PJD030"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1402138"],"award-info":[{"award-number":["25ZR1402138"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3600507","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:15:55Z","timestamp":1755627355000},"page":"11400-11416","source":"Crossref","is-referenced-by-count":6,"title":["MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"first","affiliation":[{"name":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5684","authenticated-orcid":false,"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China"}]},{"given":"Kaining","family":"Ying","sequence":"additional","affiliation":[{"name":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9104-2315","authenticated-orcid":false,"given":"Xudong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00138"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01406"},{"key":"ref20","article-title":"Bootstrapping referring multi-object tracking","author":"Zhang","year":"2024"},{"key":"ref21","article-title":"GIT: A generative image-to-text transformer for vision and language","volume-title":"Trans. Mach. Learn. Res.","author":"Wang","year":"2022"},{"key":"ref22","first-page":"72842","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Chen","year":"2023"},{"key":"ref23","first-page":"1","article-title":"NarrativeBridge: Enhancing video captioning with causal-temporal narrative","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nadeem","year":"2025"},{"key":"ref24","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref25","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Heo","year":"2022"},{"key":"ref26","article-title":"Tracking with human-intent reasoning","author":"Zhu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00105"},{"key":"ref51","article-title":"Dronescapes dataset","author":"Marcu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01144"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3159403"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref64","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref65","article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","author":"Liang","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_12"},{"key":"ref69","article-title":"Seed-TTS: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01810"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00310"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3437645"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897766"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6881"},{"key":"ref89","first-page":"38728","article-title":"mPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00048"},{"key":"ref91","first-page":"1","article-title":"Dense video object captioning from disjoint supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2025"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref95","article-title":"VIDiff: Translating videos via multi-modal instructions with diffusion models","author":"Xing","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_24"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3434373"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01280"},{"key":"ref99","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref100","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref101","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref103","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref105","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref109","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref115","first-page":"26425","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Luo","year":"2023"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"ref117","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11130435.pdf?arnumber=11130435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:58:18Z","timestamp":1762408698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":119,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3600507","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":[[2025,12]]}}}