{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:35Z","timestamp":1761894695786,"version":"build-2065373602"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210049","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Detecting AI-Generated Video via Frame Consistency"],"prefix":"10.1109","author":[{"given":"Long","family":"Ma","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,School of Cyber Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Yan","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglang","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Cyber Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Cyber Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University,School of Software Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Aarhus University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app131910980"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/3300000041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"year":"2024","key":"ref11","article-title":"Sora"},{"year":"2024","key":"ref12","article-title":"Veo"},{"year":"2024","key":"ref13","article-title":"Kling"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"issue":"2","key":"ref17","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"article-title":"Modelscope text-to-video technical report","year":"2023","author":"Wang","key":"ref19"},{"year":"2023","key":"ref20","article-title":"zero"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"article-title":"Make-a-video: Text-to-video generation without text-video data","year":"2022","author":"Singer","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref24","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"International conference on machine learning","author":"Frank"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"article-title":"Df40: Toward next-generation deepfake detection","year":"2024","author":"Yan","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"article-title":"Deepfakebench: A comprehensive benchmark of deepfake detection","year":"2023","author":"Yan","key":"ref31"},{"key":"ref32","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"article-title":"Fetv: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Liu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"issue":"11","key":"ref36","article-title":"Visualizing data using t-sne","volume":"9","author":"der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref37"},{"article-title":"Deep image fingerprint: Accurate and low budget synthetic image detector","year":"2023","author":"Sinitsa","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210049.pdf?arnumber=11210049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:29Z","timestamp":1761888809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210049","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}