{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:04:33Z","timestamp":1770933873011,"version":"3.50.1"},"reference-count":120,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":"Key Project of National Natural Science Foundation of China","award":["62406231"],"award-info":[{"award-number":["62406231"]}]},{"name":"Key Project of National Natural Science Foundation of China","award":["62231027"],"award-info":[{"award-number":["62231027"]}]},{"name":"Joint Fund Project of National Natural Science Foundation of China","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20232033"],"award-info":[{"award-number":["GZC20232033"]}]},{"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-Machine Hybrid Augmented Intelligence, Xi\u2019an Jiaotong University","award":["HMHAI-202404"],"award-info":[{"award-number":["HMHAI-202404"]}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education and the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi\u2019an Jiaotong University","award":["HMHAI-202405"],"award-info":[{"award-number":["HMHAI-202405"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["YJSJ25004"],"award-info":[{"award-number":["YJSJ25004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYTS25211"],"award-info":[{"award-number":["ZYTS25211"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Fund of Xidian University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3601180","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:31:40Z","timestamp":1755801100000},"page":"2232-2246","source":"Crossref","is-referenced-by-count":1,"title":["ERFC: Energy-Aware Reinforcement Feedback Calibration for Zero-Shot Captioning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2002-3894","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8872-2195","authenticated-orcid":false,"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"ref2","article-title":"Language models can see: Plugging visual controls in text generation","author":"Su","year":"2022","journal-title":"arXiv:2205.02655"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3371376"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581174"},{"key":"ref10","article-title":"Zero-shot video captioning with evolving pseudo-tokens","author":"Tewel","year":"2022","journal-title":"arXiv:2207.11100"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3335859"},{"key":"ref13","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref14","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref15","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref18","article-title":"Diagnosing and rectifying vision models using language","author":"Zhang","year":"2023","journal-title":"arXiv:2302.04269"},{"key":"ref19","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref20","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref22","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2023","journal-title":"arXiv:2305.18010"},{"key":"ref23","article-title":"RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback","author":"Lee","year":"2023","journal-title":"arXiv:2309.00267"},{"key":"ref24","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.705"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref28","article-title":"A tutorial on energy-based learning","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref29","article-title":"How to train your energy-based models","author":"Song","year":"2021","journal-title":"arXiv:2101.03288"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref32","first-page":"33229","article-title":"Tuning computer vision models with task rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref33","first-page":"3603","article-title":"Implicit generation and modeling with energy based models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Du"},{"key":"ref34","first-page":"12275","article-title":"Your GAN is secretly an energy-based model and you should use discriminator driven latent sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Che"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref37","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling"},{"key":"ref38","first-page":"9538","article-title":"COLD decoding: Energy-based constrained text generation with Langevin dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref44","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3194869"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10874-4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3135248"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232634"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3399933"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277827"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408684"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402242"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218104"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref67","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3576486"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347093"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296196"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3386339"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111452"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3516778"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2918591"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR55827.2022.00037"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3392013"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317518"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110744"},{"key":"ref83","article-title":"SOVC: Subject-oriented video captioning","author":"Teng","year":"2023","journal-title":"arXiv:2312.13330"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112258"},{"issue":"8","key":"ref87","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112170"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00887"},{"key":"ref90","article-title":"A distributional approach to controlled text generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Khalifa"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref92","article-title":"Your classifier is secretly an energy based model and you should treat it like one","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Grathwohl"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02256"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658112"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-6"},{"key":"ref96","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.222"},{"key":"ref99","article-title":"Statistical physics, course of theoretical physics","volume":"9","author":"Lifshitz","year":"1980","journal-title":"Part 2: Theory of the Condensed State"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref106","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":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref109","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096424"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28260"},{"key":"ref112","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref113","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Zeng","year":"2024","journal-title":"arXiv:2406.12793"},{"issue":"11","key":"ref114","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00308"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11133665.pdf?arnumber=11133665","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:30Z","timestamp":1770930150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133665\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":120,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3601180","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}