{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:00:57Z","timestamp":1784923257544,"version":"3.55.0"},"reference-count":105,"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":[{"name":"Key Project of National Natural Science Foundation of China","award":["62431020"],"award-info":[{"award-number":["62431020"]}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"name":"Fund for Foreign Scholars in University Research and Teaching Programs","award":["B07048"],"award-info":[{"award-number":["B07048"]}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education and the National Key Laboratory of Human\u2013Machine Hybrid Augmented Intelligence, Xi\u2019an Jiaotong University","award":["HMHAI- 202404"],"award-info":[{"award-number":["HMHAI- 202404"]}]},{"name":"Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University","award":["YJSJ25004"],"award-info":[{"award-number":["YJSJ25004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3713012","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T20:22:21Z","timestamp":1784578941000},"page":"7813-7827","source":"Crossref","is-referenced-by-count":0,"title":["RefZVC: Refinable Zero-Shot Video Captioning by Test-Time Reinforcement Polishing"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"first","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3307969"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112258"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110744"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185320"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3607837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3601180"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3576486"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3516778"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3586118"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3581174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"ref29","article-title":"Revisiting image captioning training paradigm via direct CLIP-based optimization","author":"Moratelli","year":"2024","journal-title":"arXiv:2408.14547"},{"key":"ref30","article-title":"Language models can see: Plugging visual controls in text generation","author":"Su","year":"2022","journal-title":"arXiv:2205.02655"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.664"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"ref35","first-page":"1","article-title":"DeCap: Decoding clip latents for zero-shot captioning via text-only training","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3371376"},{"issue":"8","key":"ref37","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref38","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref39","first-page":"429","article-title":"Zero-shot video captioning by evolving pseudo-tokens","volume-title":"Proc. BMVC","author":"Tewel"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112170"},{"key":"ref41","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref43","first-page":"33229","article-title":"Tuning computer vision models with task rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref44","article-title":"RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback","author":"Lee","year":"2023","journal-title":"arXiv:2309.00267"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0470"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.705"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref49","first-page":"3597","article-title":"Test-time adaptation with clip reward for zero-shot generalization in vision-language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148868"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452437"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref55","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00564"},{"key":"ref57","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Chen"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3233\/faia200204"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00308"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3145158"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2813306"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10874-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408684"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3289293"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3135248"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3349868"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3014312"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3383057"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3386339"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3174873"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402242"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111452"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185638"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3034233"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01816"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3159472"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3261659"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref88","first-page":"33080","article-title":"Vision-centric token compression in large language model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Xing"},{"key":"ref89","first-page":"4793","article-title":"Directly fine-tuning diffusion models on differentiable rewards","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Clark"},{"key":"ref90","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3323491"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3616201"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112170"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref102","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":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref104","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"GLM","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3629609"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11614683.pdf?arnumber=11614683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:01:54Z","timestamp":1784919714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11614683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3713012","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}