{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:26:16Z","timestamp":1764656776441,"version":"3.46.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,29]]},"DOI":"10.1109\/ispa66905.2025.11259101","type":"proceedings-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:23:30Z","timestamp":1764613410000},"page":"193-198","source":"Crossref","is-referenced-by-count":0,"title":["AI-Generated Video Quality Assessment: Dataset and Analysis"],"prefix":"10.1109","author":[{"given":"P.","family":"Rabuzin","sequence":"first","affiliation":[{"name":"University North,Department of Multimedia,Varaždin,Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Dumic","sequence":"additional","affiliation":[{"name":"University North,Department of Electrical Engineering,Varaždin,Croatia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Sora: Creating video from text","volume-title":"OpenAI","year":"2025","key":"ref1"},{"article-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR 2025)","author":"Yang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11331-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/contel.2015.7231203"},{"journal-title":"International Telecommunications Union","article-title":"Methodology for the subjective assessment of the quality of television pictures,","year":"2023","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0441-2"},{"key":"ref10","first-page":"65","article-title":"Reduced video quality measure based on 3D steerable wavelet transform and modified structural similarity index,","volume-title":"Proceedings ELMAR-2013","author":"Dumic"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s19214655"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4133-3","article-title":"Perceptual video quality assessment: a survey","volume":"67","author":"Min","year":"2024","journal-title":"Science China Information Sciences"},{"key":"ref13","article-title":"A survey of AI-generated video evaluation","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3749844"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2024.110514"},{"key":"ref17","first-page":"62352","article-title":"FETV: a benchmark for fine-grained evaluation of opendomain text-to-video generation","volume-title":"In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923)","author":"Liu"},{"article-title":"CogVideoX-5B","volume-title":"CogVideoX-5B Huggingface Space","year":"2025","key":"ref18"},{"article-title":"Text2Video-Zero","volume-title":"Picsart AI Research (PAIR)","year":"2025","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2018.2886771"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00372"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00510"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2012.2227726"},{"key":"ref27","first-page":"54015","article-title":"Q-ALIGN: teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"In Proceedings of the 41st International Conference on Machine Learning (ICML\u201924)","volume":"235","author":"Wu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3378466"},{"volume-title":"IQA-PyTorch: PyTorch Toolbox for Image Quality Assessment","year":"2025","author":"Chen","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00589"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01843"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3319332"},{"article-title":"COVER: A Comprehensive Video Quality Evaluator","volume-title":"Trustworthy, Autonomous, Human-Centered, Embodied (TACO) Intelligence Group","year":"2025","key":"ref35"},{"volume-title":"DOVER","year":"2025","author":"Wu","key":"ref36"},{"article-title":"FineVQ: Fine-Grained User Generated Content Video Quality Assessment","volume-title":"Intelligent Media Group (IntMeGroup)","year":"2025","key":"ref37"},{"volume-title":"Open Source Deep End-to-End Video Quality Assessment Toolbox","year":"2025","author":"Wu","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref40","first-page":"19730","article-title":"BLIP-2: bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"In Proceedings of the 40th International Conference on Machine Learning (ICML\u201923)","volume":"202","author":"Li"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (PMLR)","volume":"139","author":"Radford","year":"2021"}],"event":{"name":"2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)","start":{"date-parts":[[2025,10,29]]},"location":"Coimbra, Portugal","end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11259440\/11259097\/11259101.pdf?arnumber=11259101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:22:19Z","timestamp":1764656539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11259101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ispa66905.2025.11259101","relation":{},"subject":[],"published":{"date-parts":[[2025,10,29]]}}}