{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:40:18Z","timestamp":1777336818453,"version":"3.51.4"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2023836"],"award-info":[{"award-number":["BE2023836"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3010302"],"award-info":[{"award-number":["2023YFC3010302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82571165"],"award-info":[{"award-number":["82571165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133530","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T23:54:15Z","timestamp":1775260455000},"page":"133530","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Detecting AI-generated videos via global semantic awareness and inter-frame semantic consistency"],"prefix":"10.1016","volume":"684","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2858-0104","authenticated-orcid":false,"given":"Qianyu","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhe","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yining","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133530_bib1","series-title":"Proc","first-page":"22445","article-title":"Dire for diffusion-generated image detection","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133530_bib2","article-title":"\"A sanity check for AI-generated image detection","author":"Yan","year":"2025","journal-title":"Proc. Int. Conf. Learn. Represent. (ICLR)"},{"key":"10.1016\/j.neucom.2026.133530_bib3","article-title":"Video generation models as world simulators,\u201d OpenAI","author":"Brooks","year":"2024","journal-title":"Tech. Rep."},{"issue":"0","key":"10.1016\/j.neucom.2026.133530_bib4","volume":"1","author":"Pika","year":"2023","journal-title":"Inc. \u201cPika"},{"key":"10.1016\/j.neucom.2026.133530_bib5","unstructured":"Kuaishou Technology, \u201cKling,\u201d Jun. 2024. [Online]. Available: \u3008https:\/\/kling.kuaishou.com\/\u3009."},{"key":"10.1016\/j.neucom.2026.133530_bib6","doi-asserted-by":"crossref","unstructured":"D.S. Vahdati, T.D. Nguyen, A. Azizpour, and M.C. Stamm, \"Beyond Deepfake Images: Detecting AI-Generated Videos,\" in Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Seattle, WA, USA, Jun. 2024, pp. 4397\u20134408, doi: 10.1109\/CVPRW63382.2024.00443.","DOI":"10.1109\/CVPRW63382.2024.00443"},{"key":"10.1016\/j.neucom.2026.133530_bib7","first-page":"460","article-title":"AI-generated video detection via spatial-temporal anomaly learning","author":"Bai","year":"2024","journal-title":"Proc. Chin. Conf. Pattern Recognit. Comput. Vis. (PRCV)"},{"key":"10.1016\/j.neucom.2026.133530_bib8","article-title":"\"Detecting AI-generated video via frame consistency","author":"Ma","year":"2025","journal-title":"Proc. IEEE Int. Conf. Multimed. Expo. (ICME)"},{"key":"10.1016\/j.neucom.2026.133530_bib9","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"10.1016\/j.neucom.2026.133530_bib10","first-page":"402","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","author":"Teed","year":"2020","journal-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)"},{"key":"10.1016\/j.neucom.2026.133530_bib11","author":"Ji","year":"2024","journal-title":"Disting. any fake Video. Unleashing Power Large-Scale data Motion Features"},{"key":"10.1016\/j.neucom.2026.133530_bib12","series-title":"Proc","first-page":"3202","article-title":"Video Swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133530_bib13","author":"Chang","year":"2024","journal-title":"What Matters Detect. AI-Gener. Videos Sora"},{"key":"10.1016\/j.neucom.2026.133530_bib14","doi-asserted-by":"crossref","unstructured":"J. Battocchio, S. Dell\u2019Anna, A. Montibeller, and G. Boato, \u201cAdvance fake video detection via vision transformers,\u201d in Proc. ACM Workshop Inf. Hiding Multimedia Secur. (IH&MMSec), Jun. 2025, pp. 1\u201311.","DOI":"10.1145\/3733102.3733129"},{"key":"10.1016\/j.neucom.2026.133530_bib15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"Proc. Int. Conf. Learn. Represent. (ICLR)"},{"key":"10.1016\/j.neucom.2026.133530_bib16","unstructured":"H. Chen et al., \u201cDemamba: AI-generated video detection on million-scale GenVideo benchmark,\u201d arXiv:2405.19707, 2024."},{"key":"10.1016\/j.neucom.2026.133530_bib17","unstructured":"P. He, L. Zhu, J. Li, S. Wang, and H. Li, \u201cExposing AI-generated videos: A benchmark dataset and a local-and-global temporal defect based detection method,\u201d arXiv:2405.04133, 2024."},{"key":"10.1016\/j.neucom.2026.133530_bib18","author":"Peng","year":"2022","journal-title":"BEiT v2 Masked Image Model. Vector-quantized Vis. tokenizers"},{"key":"10.1016\/j.neucom.2026.133530_bib19","first-page":"53709","article-title":"On learning multi-modal forgery representation for diffusion generated video detection","author":"Song","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.133530_bib20","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit","article-title":"Turns out I\u2019m not real: Towards robust detection of AI-generated videos","author":"Liu","year":"2024"},{"issue":"11","key":"10.1016\/j.neucom.2026.133530_bib21","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"issue":"8","key":"10.1016\/j.neucom.2026.133530_bib22","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.133530_bib23","author":"Liu","year":"2025","journal-title":"Lavid Agent. lvlm Framew. Diffus. -Gener. Video Detect."},{"key":"10.1016\/j.neucom.2026.133530_bib24","unstructured":"H. Wen et al., \u201cBusterX: MLLM-powered AI-generated video forgery detection and explanation,\u201d arXiv:2505.12620, 2025."},{"key":"10.1016\/j.neucom.2026.133530_bib25","author":"Xu","year":"2025","journal-title":"Avatar. Vis. Reinf. Learn. Hum. -Centr Video Forg. Detect."},{"key":"10.1016\/j.neucom.2026.133530_bib26","doi-asserted-by":"crossref","unstructured":"T. Song, T. Hu, G. Gan, and Y. Zhao, \"VF-Eval: Evaluating multimodal LLMs for generating feedback on AIGC videos,\" in Proc. Annu. Meeting Assoc. Comput. Linguistics (ACL), 2025.","DOI":"10.18653\/v1\/2025.acl-long.1027"},{"key":"10.1016\/j.neucom.2026.133530_bib27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.133530_bib28","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.133530_bib29","author":"Sun","year":"2024","journal-title":"Sora what we Can. see A Surv. Text. -to-Video Gener."},{"key":"10.1016\/j.neucom.2026.133530_bib30","author":"Blattmann","year":"2023","journal-title":"Stable Video Diffus. Scaling latent Video Diffus. Models Large datasets"},{"key":"10.1016\/j.neucom.2026.133530_bib31","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.133530_bib32","series-title":"Proc","first-page":"6836","article-title":"ViViT: A video vision transformer","author":"Arnab","year":"2021"},{"issue":"3","key":"10.1016\/j.neucom.2026.133530_bib33","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00030","article-title":"Multimodal neurons in artificial neural networks","volume":"6","author":"Goh","year":"2021","journal-title":"Distill"},{"key":"10.1016\/j.neucom.2026.133530_bib34","series-title":"Proc","first-page":"3644","article-title":"Defense-prefix for preventing typographic attacks on CLIP","author":"Azuma","year":"2023"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009276?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009276?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T23:46:32Z","timestamp":1777333592000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226009276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":34,"alternative-id":["S0925231226009276"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133530","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Detecting AI-generated videos via global semantic awareness and inter-frame semantic consistency","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133530","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133530"}}