{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T14:18:58Z","timestamp":1778077138298,"version":"3.51.4"},"reference-count":86,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00416","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4273-4284","source":"Crossref","is-referenced-by-count":1,"title":["ExDDV: A New Dataset for Explainable Deepfake Detection in Video"],"prefix":"10.1109","author":[{"given":"Vlad","family":"Hondru","sequence":"first","affiliation":[{"name":"University of Bucharest,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduard","family":"Hogea","sequence":"additional","affiliation":[{"name":"West University of Timişoara,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darian","family":"Onchi\u015f","sequence":"additional","affiliation":[{"name":"West University of Timişoara,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu Tudor","family":"Ionescu","sequence":"additional","affiliation":[{"name":"University of Bucharest,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3369412.3395070"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of ACL","author":"Banerjee"},{"key":"ref6","author":"Barrus","year":"2024","journal-title":"pyspellchecker - Pure Python Spell Checking Library"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01197"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref12","first-page":"249","article-title":"Re-evaluating the Role of BLEU in Machine Translation Research","volume-title":"Proceedings of EACL","author":"Callison-Burch"},{"key":"ref13","article-title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","author":"Chen","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01483"},{"key":"ref19","article-title":"Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook","author":"Croitoru","year":"2024"},{"key":"ref20","article-title":"MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark","author":"Croitoru","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00471"},{"key":"ref22","article-title":"The deepfake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020"},{"key":"ref23","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proceedings of ICLR","author":"Dosovitskiy"},{"key":"ref24","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question answering","volume-title":"Proceedings of NeurIPS","author":"Gao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19955"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_35"},{"key":"ref27","first-page":"4517","article-title":"Delving into sequential patches for deepfake detection","volume-title":"Proceedings of NeurIPS","author":"Guan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proceedings of ICLR","author":"Hu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19978"},{"key":"ref34","article-title":"Explainable Deepfake Video Detection using Convolutional Neural Network and CapsuleNet","author":"Ishrak","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.409"},{"key":"ref36","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref38","article-title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","volume-title":"Proceedings of NeurIPS","author":"Khalid"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1011"},{"key":"ref40","first-page":"12888","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"Proceedings of ICML","author":"Li"},{"key":"ref41","first-page":"19730","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"Proceedings of ICML","author":"Li"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref43","article-title":"ROUGE: A Package for Automatic Evaluation of summaries","volume-title":"Proceedings of ACL","author":"Lin"},{"key":"ref44","article-title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00467"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681198"},{"key":"ref48","first-page":"13807","article-title":"Rethinking Attention-Model Explain-ability through Faithfulness Violation Test","volume-title":"Proceedings of ICML","author":"Liu"},{"key":"ref49","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proceedings of NeurIPS","author":"Lundberg"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01583"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10442"},{"key":"ref52","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proceedings of NeurIPS","author":"Malinowski"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref55","article-title":"Large Language Models: A Survey","author":"Minaee","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00342"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref59","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proceedings of NeurIPS","author":"Ouyang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.27"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref62","article-title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","author":"Piergiovanni","year":"2022"},{"key":"ref63","article-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of ICML","author":"Radford"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref66","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proceedings of NeurIPS","author":"Ren"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref69","first-page":"80","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume-title":"Proceedings of CVPR","author":"Sabir"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref72","first-page":"244","article-title":"EMO: Emote Portrait Alive \u2013 Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","volume-title":"Proceedings of ECCV","author":"Tian"},{"key":"ref73","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref75","article-title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation","author":"Wang","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26701"},{"key":"ref77","article-title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","author":"Xu","year":"2024"},{"key":"ref78","first-page":"660","article-title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","volume-title":"Proceedings of NeurIPS","author":"Xu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01177"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref81","article-title":"BERTScore: Evaluating Text Generation with BERT","volume-title":"Proceedings of ICLR","author":"Zhang"},{"key":"ref82","article-title":"Mimic-Motion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","author":"Zhang","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41579-2_37"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref85","article-title":"Fine-grained sentiment analysis with faithful attention","author":"Zhong","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492397.pdf?arnumber=11492397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:22Z","timestamp":1778046982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00416","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}