ACL Findings2026
Detecting AI-Generated Video: A Vision-Language Dual-View Survey
Dylan Xinming Hou, Juntian Zhang, Xu Gu, Yichen Wu, Nils Lukas, Gus Xia, Xiuying Chen, Yuhan Liu
Abstract
The evolving realism of AI-generated videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing the task as Factual Fidelity Verification, which asks whether the events, entities, and physical processes depicted in a video are consistent with real-world facts. To systematize this rapidly evolving field, we propose a Vision-Language Dual-View taxonomy that organizes existing methods into a hierarchical, four-layer landscape spanning intrinsic cue analysis, spatiotemporal consistency modeling, cross-modal consistency reasoning, and language-guided worldlevel reasoning. This dual-view framing highlights a fundamental transition from artifact matching in traditional deepfake detection to evidence-based semantic verification enabled by vision-language models and agentic reasoning pipelines. Based on a systematic review of 221 works as of March 2026, we synthesize AIGC-V generation paradigms, survey the landscape of detection methods, and review evaluation metrics and benchmarks in line with the proposed views. Finally, we discuss current challenges and identify promising directions toward robust, explainable, and trustworthy detection. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Emotions Don't Lie: An Audio-Visual Deepfake Detection Method using Affective Cues cites FaceForensics++: Learning to Detect Manipulated Facial Images
- WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
Builds on71
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- FaceForensics++: Learning to Detect Manipulated Facial ImagesAndreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess et al.ICCV 2019 · 2,966 citations
- Video Diffusion ModelsJonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan et al.NeurIPS 2022 · 2,948 citations
- WildDeepfake: A Challenging Real-World Dataset for Deepfake DetectionBojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma et al.ACM MM 2020 · 443 citations
- Emotions Don't Lie: An Audio-Visual Deepfake Detection Method using Affective CuesTrisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera et al.ACM MM 2020 · 314 citations
Related papers
- Semantic Visual Anomaly Detection and Reasoning in AI-Generated ImagesChuangchuang Tan, Xiang Ming, Jinglu Wang, Renshuai Tao et al.ICLR 2026 · 7 citations
- FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and ContentYifeng Gao, Yifan Ding, Li Wang, Feida Huang et al.ICML 2026
- CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video DetectionHuidong Feng, Wentao Chen, Jie Chen, Xinqi Cai et al.CVPR 2026 · 2 citations
- Your One-Stop Solution for AI-Generated Video DetectionLong Ma, Zihao Xue, Yan Wang, Zhiyuan Yan et al.CVPR 2026 · 13 citations
- Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language ModelsZheyuan Gu, Qingsong Zhao, Yusong Wang, Zhaohong Huang, Xinqi Li, Chen Yuan, Jiawei Shao, Chi Zhang, Xuelong LiCVPR Findings 2026
