{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T21:07:30Z","timestamp":1772658450718,"version":"3.50.1"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"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":[[2025,9,8]]},"DOI":"10.1109\/ijcb65343.2025.11410820","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:39Z","timestamp":1772571039000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Detecting Hyper-Realistic Videos Generated by Diffusion Models via Text-Guided Semantic Enhancement"],"prefix":"10.1109","author":[{"given":"Shum Hing","family":"Ling","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Kumar","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Web link to download hyper-realistic videos dataset","year":"2025"},{"key":"ref2","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00053"},{"key":"ref4","article-title":"Human action clips: Detecting aigenerated human motion","author":"Bohacek","year":"2024"},{"key":"ref5","article-title":"Deepfake-eval-2024: A multi-modal in-the-wild benchmark of deepfakes circulated in 2024","author":"Chandra","year":"2025"},{"key":"ref6","article-title":"What matters in detecting ai-generated videos like sora\u0192","author":"Chang","year":"2024"},{"key":"ref7","article-title":"Demamba: Ai-generated video detection on million-scale genvideo benchmark","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446290"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3294357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00771"},{"key":"ref13","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"International conference on machine learning","author":"Frank"},{"key":"ref14","volume-title":"Open images v7 dataset","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105418"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32363"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref19","article-title":"Comprehensive deepfake detection dataset: Real and synthetic frames from roop and akool ai technologies","volume":"V1","author":"Islam","year":"2025","journal-title":"Mendeley Data"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00293"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10810-6"},{"key":"ref23","volume-title":"Kling ai","author":"Kling"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747628"},{"key":"ref25","volume-title":"Iris and Periocular Recognition Using Deep Learning","author":"Kumar","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02612"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01024"},{"key":"ref28","article-title":"Turns out i\u2019m not real: Towards robust detection of ai-generated videos","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Lavid: An agentic lvlm framework for diffusion-generated video detection","author":"Liu","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00051"},{"key":"ref31","volume-title":"Luma dream machine: New freedoms of imagination","author":"Luma"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.173273016.63626046\/v1","article-title":"Passive deepfake detection across multi-modalities: A comprehensive survey","author":"Nguyen-Le","year":"2024"},{"key":"ref33","article-title":"Genvidbench: A challenging benchmark for detecting ai-generated video","author":"Ni","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref35","volume-title":"Sora"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755592"},{"key":"ref38","volume-title":"Pika"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref41","volume-title":"Tools for human imagination"},{"key":"ref42","article-title":"On learning multi-modal forgery representation for diffusion generated video detection","author":"Song","year":"2024"},{"key":"ref43","volume-title":"stable-video-diffusion-img2vid-xt"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00443"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2025.3641104"},{"key":"ref50","article-title":"Generalizable ai-generated image detection based on fractal self-similarity in the spectrum","author":"Xiao","year":"2025"},{"key":"ref51","article-title":"Unlocking the hidden potential of clip in generalizable deepfake detection","author":"Yermakov","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"ref53","article-title":"Chameleon: On the scene diversity and domain variety of ai-generated videos detection","author":"Zeng","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02034"},{"key":"ref57","article-title":"Survey on ai-generated media detection: From non-mllm to mllm","author":"Zou","year":"2025"}],"event":{"name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","location":"Osaka, Japan","start":{"date-parts":[[2025,9,8]]},"end":{"date-parts":[[2025,9,11]]}},"container-title":["2025 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410556\/11410616\/11410820.pdf?arnumber=11410820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:37Z","timestamp":1772657257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11410820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ijcb65343.2025.11410820","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]}}}