{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:00:19Z","timestamp":1776114019057,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":"publisher","award":["62461028"],"award-info":[{"award-number":["62461028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20220"],"award-info":[{"award-number":["U24A20220"]}],"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":[[2026,4]]},"DOI":"10.1109\/tcsvt.2026.3651308","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"5398-5408","source":"Crossref","is-referenced-by-count":0,"title":["Objective Quality Assessment of AI-Generated Content Videos With Transformation Consistency Focus"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9437-7639","authenticated-orcid":false,"given":"Xiaoyu","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0337-6877","authenticated-orcid":false,"given":"Jiebin","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3586","authenticated-orcid":false,"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref2","article-title":"Phenaki: Variable length video generation from open domain textual description","author":"Villegas","year":"2022","journal-title":"arXiv:2210.02399"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref4","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i8.37599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272480"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532513"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3077642"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3450085"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445770"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102956"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"key":"ref23","first-page":"1","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00290"},{"key":"ref25","article-title":"GODIVA: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv:2104.14806"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177127"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02079"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref29","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02227"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"ref36","article-title":"A-bench: Are LMMs masters at evaluating AI-generated images?","author":"Zhang","year":"2024","journal-title":"arXiv:2406.03070"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3749844"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"ref39","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":"ref40","article-title":"AGAV-rater: Adapting large multimodal model for AI-generated audio-visual quality assessment","author":"Cao","year":"2025","journal-title":"arXiv:2501.18314"},{"key":"ref41","article-title":"Towards generalized video quality assessment: A weak-to-strong learning paradigm","author":"Cao","year":"2025","journal-title":"arXiv:2505.03631"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3571788"},{"key":"ref43","article-title":"Video quality assessment: A comprehensive survey","author":"Zheng","year":"2024","journal-title":"arXiv:2412.04508"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1167\/17.1.32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2024.117101"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3215311"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00589"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref55","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":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref58","article-title":"MANTIS: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv:2405.01483"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00640"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00659"},{"key":"ref61","article-title":"TC-bench: Benchmarking temporal compositionality in text-to-video and image-to-video generation","author":"Feng","year":"2024","journal-title":"arXiv:2406.08656"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2039"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3483"},{"key":"ref64","volume-title":"The Perception of the Visual World","author":"Gibson","year":"1950"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref72","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref73","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref74","first-page":"1","article-title":"FETV: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref75","article-title":"Measuring the quality of text-to-video model outputs: Metrics and dataset","author":"Chivileva","year":"2023","journal-title":"arXiv:2309.08009"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref77","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv:2307.04725"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref81","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":"ref82","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":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11333377.pdf?arnumber=11333377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:38:28Z","timestamp":1776109108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":83,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3651308","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}