{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T05:06:53Z","timestamp":1774674413981,"version":"3.50.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62522116"],"award-info":[{"award-number":["62522116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62271312"],"award-info":[{"award-number":["62271312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"crossref","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3618655","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:53:08Z","timestamp":1759859588000},"page":"3367-3381","source":"Crossref","is-referenced-by-count":1,"title":["LMVQ: Label-Free Metric-Learning for General AI-Generated Video Quality Assessment"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1466-6383","authenticated-orcid":false,"given":"Zhichao","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7362-0532","authenticated-orcid":false,"given":"Xinyue","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6377-4730","authenticated-orcid":false,"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3532495"},{"key":"ref2","volume-title":"Sora","year":"2024"},{"key":"ref3","volume-title":"Wanxiang","author":"Cloud","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref5","article-title":"Human-activity AGV quality assessment: A benchmark dataset and an objective evaluation metric","author":"Zhang","year":"2024","journal-title":"arXiv:2411.16619"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3749844"},{"key":"ref7","article-title":"AIGV-assessor: Benchmarking and evaluating the perceptual quality of text-to-video generation with LMM","author":"Wang","year":"2024","journal-title":"arXiv:2411.17221"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1267"},{"key":"ref9","volume-title":"Methodology for the Subjective Assessment of the Quality of Television Pictures","year":"2002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00513"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3130536"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548064"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310344"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1122"},{"key":"ref18","first-page":"1","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref19","first-page":"1","article-title":"Phenaki: Variable length video generation from open domain textual description","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Villegas"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"issue":"3","key":"ref21","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref23","article-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2303.07909"},{"key":"ref24","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho"},{"key":"ref25","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref28","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv:2310.19512"},{"key":"ref29","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref30","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv:2408.06072"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.25"},{"key":"ref32","volume-title":"Kling","author":"Technology","year":"2024"},{"key":"ref33","volume-title":"Ying","author":"AI","year":"2024"},{"key":"ref34","volume-title":"Dreamina","year":"2024"},{"key":"ref35","article-title":"From sora what we can see: A survey of text-to-video generation","author":"Sun","year":"2024","journal-title":"arXiv:2405.10674"},{"key":"ref36","article-title":"Sora as an AGI world model? A complete survey on text-to-video generation","author":"Cho","year":"2024","journal-title":"arXiv:2403.05131"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207148"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225552"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367904"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3418941"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900472"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28221"},{"key":"ref54","article-title":"T2 V-CompBench: A comprehensive benchmark for compositional Text-to-video generation","author":"Sun","year":"2024","journal-title":"arXiv:2407.14505"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00541"},{"key":"ref56","first-page":"62352","article-title":"FETV: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref60","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref68","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref69","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","author":"Wu","year":"2023","journal-title":"arXiv:2312.17090"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref71","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref72","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref73","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref74","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"ref76","article-title":"VisionReward: Fine-grained multi-dimensional human preference learning for image and video generation","author":"Xu","year":"2024","journal-title":"arXiv:2412.21059"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref78","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref79","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref80","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref86","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref87","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv:2405.20797"},{"key":"ref88","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv:2504.10479"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11195854.pdf?arnumber=11195854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:46Z","timestamp":1773086446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":90,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3618655","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}