{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:54Z","timestamp":1777888794704,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62402171,62472434"],"award-info":[{"award-number":["62402171,62472434"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01302","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14028-14038","source":"Crossref","is-referenced-by-count":0,"title":["HumanSAM: Classifying Human-Centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly"],"prefix":"10.1109","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfan","family":"Ye","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchuan","family":"Luo","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiping","family":"Cai","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8792-0_32"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref4","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref6","article-title":"What matters in detecting ai-generated videos like sora?","author":"Chang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106807"},{"key":"ref8","article-title":"Videojam: Joint appearance-motion representations for enhanced motion generation in video models","author":"Chefer","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"ref12","article-title":"Venhancer: Generative space-time enhancement for video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref15","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref17","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref22","first-page":"1083","article-title":"Blind video temporal consistency via deep video prior","volume":"33","author":"Lei","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"A comprehensive survey on human video generation: Challenges, methods, and insights","author":"Lei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref26","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref29","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02481"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Segment anything in images and videos","volume":"2","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616588"},{"key":"ref36","article-title":"Repvideo: Rethinking crosslayer representation for video generation","author":"Si","year":"2025","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"On learning multi-modal forgery representation for diffusion generated video detection","volume-title":"Proceeding of Thirty-eighth Conference on Neural Information Processing Systems","author":"Song"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref46","article-title":"Scaling video foundation models for multimodal video understanding","volume":"2","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00060"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3594034"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref52","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3292905"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28490"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3449920"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01211"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01646"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3545625"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446067.pdf?arnumber=11446067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:23Z","timestamp":1777611503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01302","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}