{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T05:43:59Z","timestamp":1785822239904,"version":"3.56.0"},"reference-count":68,"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":"crossref","award":["62406263"],"award-info":[{"award-number":["62406263"]}],"id":[{"id":"10.13039\/501100001809","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.2026.3715157","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T19:02:40Z","timestamp":1785178960000},"page":"8093-8106","source":"Crossref","is-referenced-by-count":0,"title":["Scene Graph-Guided SegCaptioning Transformer With Fine-Grained Alignment for Controllable Video Segmentation and Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3632-4464","authenticated-orcid":false,"given":"Xu","family":"Zhang","sequence":"first","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9600-7789","authenticated-orcid":false,"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"BinHong","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-2466","authenticated-orcid":false,"given":"Xuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7955-3073","authenticated-orcid":false,"given":"Qianjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southwest Jiaotong University","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7273-9873","authenticated-orcid":false,"given":"Yuyi","family":"Wang","sequence":"additional","affiliation":[{"name":"CRRC Zhuzhou Institute Company Ltd.","place":["Zhuzhou, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9720-5915","authenticated-orcid":false,"given":"Zhiyong","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University","place":["Nanyang Ave, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3313932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3437645"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3338003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3492713"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2287"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3591538"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2969552"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3337970"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_26"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687937"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557710"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33113"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227466"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref26","first-page":"57040","article-title":"Dense video object captioning from disjoint supervision","volume-title":"Proc. ICLR","author":"Zhou"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3506751"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413908"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680724"},{"key":"ref30","article-title":"SOVC: Subject-oriented video captioning","author":"Teng","year":"2023","journal-title":"arXiv:2312.13330"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00311"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3419119"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2267"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552694"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32338"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_13"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128804"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3615851"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3468640"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00253"},{"key":"ref47","first-page":"28085","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. ICLR","author":"Ravi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref49","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref50","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01773"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"issue":"3","key":"ref56","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","volume":"2","author":"Chiang","year":"2023","journal-title":"See"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref58","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref65","article-title":"SAMURAI: Adapting segment anything model for zero-shot visual tracking with motion-aware memory","author":"Yang","year":"2024","journal-title":"arXiv:2411.11922"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref68","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11626023.pdf?arnumber=11626023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:47:36Z","timestamp":1785818856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11626023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3715157","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}