{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:56:38Z","timestamp":1781816198979,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tbiom.2026.3663642","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:57:45Z","timestamp":1770843465000},"page":"540-551","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Real Versus Fake: Towards Intent-Aware Video Analysis"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7572-660X","authenticated-orcid":false,"given":"Saurabh","family":"Atreya","sequence":"first","affiliation":[{"name":"BITS Pilani, Hyderabad, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nabyl","family":"Quignon","sequence":"additional","affiliation":[{"name":"Inria Centre, Université Côte d’Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7156-7632","authenticated-orcid":false,"given":"Baptiste","family":"Chopin","sequence":"additional","affiliation":[{"name":"Inria Centre, Université Côte d’Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Das","sequence":"additional","affiliation":[{"name":"BITS Pilani, Hyderabad, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-7029","authenticated-orcid":false,"given":"Antitza","family":"Dantcheva","sequence":"additional","affiliation":[{"name":"Inria Centre, Université Côte d’Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00433"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSEC.2024.3388244"},{"key":"ref3","article-title":"Detecting multimedia generated by large AI models: A survey","author":"Lin","year":"2024","journal-title":"arXiv:2402.00045"},{"key":"ref4","article-title":"Large language models as instruments of power: New regimes of autonomous manipulation and control","author":"Chaudhary","year":"2024","journal-title":"arXiv:2405.03813"},{"key":"ref5","article-title":"Frontier models are capable of in-context scheming","author":"Meinke","year":"2024","journal-title":"arXiv:2412.04984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28290"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02524"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01803"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681442"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.606"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref17","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. NeurIPS","author":"Simonyan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref19","first-page":"16139","article-title":"Uniformer: Unified transformer for efficient spatial\u2013temporal representation learning","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref21","article-title":"InternVideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv:2212.03191"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01736"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217368"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref30","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref31","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1348"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2235"},{"key":"ref35","first-page":"6751","article-title":"Grounding multimodal large language models to the world","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.855"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref41","article-title":"MM-REACT: Prompting ChatGPT for multimodal reasoning and action","author":"Yang","year":"2023","journal-title":"arXiv:2303.11381"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.98"},{"key":"ref43","article-title":"X-LLM: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023","journal-title":"arXiv:2305.04160"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref45","first-page":"22185","article-title":"Video-LaVIT: Unified video-language pre-training with decoupled visual-motional tokenization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref47","first-page":"53366","article-title":"Next-GPT: Any-to-any multimodal LLM","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref48","article-title":"Tool-LMM: A large multi-modal model for tool agent learning","author":"Wang","year":"2024","journal-title":"arXiv:2401.10727"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_6"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref52","volume-title":"Llama 3 Model Card","year":"2024"},{"key":"ref53","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Qwen","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3699710"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00110"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3239223"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3643030"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref63","article-title":"BERT for joint intent classification and slot filling","author":"Chen","year":"2019","journal-title":"arXiv:1902.10909"},{"key":"ref64","first-page":"9182","article-title":"Task-oriented dialogue with transferable multi-hop memories","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Zhang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlp4convai-1.5"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3381038"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3418340"},{"key":"ref70","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172279"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/11569824\/11393515.pdf?arnumber=11393515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:13:29Z","timestamp":1781813609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":74,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2026.3663642","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}