{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:32Z","timestamp":1783542512556,"version":"3.55.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010256","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371283"],"award-info":[{"award-number":["62371283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3673333","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:39:46Z","timestamp":1773347986000},"page":"10230-10243","source":"Crossref","is-referenced-by-count":0,"title":["Unveiling the Modular Design of Text-to-Video Quality Assessment"],"prefix":"10.1109","volume":"36","author":[{"given":"Bingkun","family":"Zheng","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3634-2630","authenticated-orcid":false,"given":"Weixia","family":"Zhang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref3","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021","journal-title":"arXiv:2104.10157"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref5","article-title":"ModelScope text-to-video technical report","volume-title":"arXiv:2308.06571","author":"Wang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref9","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":"ref10","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref12","first-page":"2226","article-title":"Improved techniques for training gans","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref13","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Heusel"},{"key":"ref14","article-title":"Fr\u00e9chet video motion distance: A metric for evaluating motion consistency in videos","author":"Liu","year":"2024","journal-title":"arXiv:2407.16124"},{"key":"ref15","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref17","article-title":"Clipscore: A reference-free evaluation metric for image captioning","author":"Hessel","year":"2022","journal-title":"arXiv:2204.09685"},{"key":"ref18","first-page":"12888","article-title":"BLIP-2: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref19","article-title":"Video quality assessment: A comprehensive survey","author":"Zheng","year":"2024","journal-title":"arXiv:2412.04508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319332"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00267"},{"key":"ref24","article-title":"No-reference screen content image quality assessment with unsupervised domain adaptation","author":"Chen","year":"2020","journal-title":"arXiv:2008.08561"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205770"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02565-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"key":"ref31","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/307"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref39","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv:2211.11018"},{"key":"ref40","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref42","article-title":"Make-A-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00616"},{"key":"ref44","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref46","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2568752"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01408-w"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00589"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref60","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":"Chen"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3749844"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00993"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00640"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"8","key":"ref71","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref72","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"key":"ref73","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv:2502.14786"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref77","first-page":"54015","article-title":"Q-Align: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"235","author":"Wu"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01350"},{"key":"ref79","first-page":"32611","article-title":"Adaptive image quality assessment via teaching large multimodal model to compare","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Chen"},{"key":"ref80","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref86","article-title":"Enhancing blind video quality assessment with rich quality-aware features","author":"Sun","year":"2024","journal-title":"arXiv:2405.08745"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref89","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref91","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref92","article-title":"EvalMuse-40K: A reliable and fine-grained benchmark with comprehensive human annotations for text-to-image generation model evaluation","author":"Han","year":"2024","journal-title":"arXiv:2412.18150"},{"key":"ref93","article-title":"PaLI: A jointly-scaled multilingual language-image model","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref94","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":"ref95","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502. 13923","author":"Bai","year":"2025"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11431223.pdf?arnumber=11431223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:27Z","timestamp":1783539927000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11431223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":95,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3673333","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}