Temporal Video Forgery Localization

Latest papers

11 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization
Jul 5, 2026Cangjin Qiu, Quan Zhang, Dan Jiang +1Frequency-Domain Feature Learning Deepfake Detection
Cangjin Qiu and Ke Zhang are with Soochow University, Suzhou, China. · Quan Zhang and Dan Jiang are with Tsinghua University, Beijing, China.
EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration
Jul 5, 2026Shen Shen, Quan Zhang, Dan Jiang +1Audio-Visual Representation Learning Digital Forensics
Soochow University · Tsinghua University
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Jul 1, 2026Jingchen Ni, Cangjin Yu, Dan Jiang +6Mixture of Experts Deepfake Detection
1Tsinghua University, China · 2Soochow University, China
Detecting Temporally Localized Manipulations in Authentic Video Streams
Jun 5, 2026Okan Umur, Ali Emre Güşlü, Ibrahim DelibasogluDeepfake Detection Temporal Video Forgery Localization
Department of Software Engineering Sakarya University Sakarya, Türkiye
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Jun 1, 2026Yue Feng, Jingjing Li, Qijia Lu +9Digital Forensics Deepfake Detection
MoE Key Laboratory of Brain-Machine Intelligence Technology, College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics · Dalian University of Technology · Independent Scholar +2
Towards multi-modal forgery representation learning for AI-generated video detection and localization
May 8, 2026Dat Le, Khoa Nguyen, Xin Wang +1Audio-Visual Representation Learning Deepfake Detection
Purdue University, West Lafayette · University at Albany, SUNY, New York
ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
Apr 4, 2026Peijun Bao, Anwei Luo, Gang Pan +2Temporal Video Forgery Localization Video Forensics
College of Computer Science and Technology, Zhejiang University · School of Electrical and Electronic Engineering, Nanyang Technological University · School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics +3
Word-Anchored Temporal Forgery Localization
Mar 6, 2026Tianyi Wang, Xi Shao, Harry Cheng +2Temporal Video Forgery Localization Audio Deepfake Detection
National University of Singapore · Nanjing University of Posts and Telecommunications · Qilu University of Technology (Shandong Academy of Sciences)
GEM-TFL: Bridging Weak and Full Supervision for Forgery Localization through EM-Guided Decomposition and Temporal Refinement
Mar 5, 2026Xiaodong Zhu, Yuanming Zheng, Suting Wang +4Temporal Video Forgery Localization Weakly Supervised Learning
NERCMS, School of Computer Science, Wuhan University
DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization
Mar 5, 2026Xiaodong Zhu, Suting Wang, Yuanming Zheng +5Hybrid Transformer-State Space Model Architectures Temporal Video Forgery Localization
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, China
Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
Feb 25, 2026Zheyuan Gu, Qingsong Zhao, Yusong Wang +6Deepfake Detection Video-Language Model Evaluation
Institute of Artificial Intelligence, China Telecom (TeleAI) · Peking University · Fudan University

Jul 5, 2026J/K move · Enter open · S save

UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization

Cangjin Qiu, Quan Zhang, Dan Jiang, Ke Zhang

Cangjin Qiu and Ke Zhang are with Soochow University, Suzhou, China. · Quan Zhang and Dan Jiang are with Tsinghua University, Beijing, China.

Frequency-Domain Feature Learning Deepfake Detection Temporal Video Forgery Localization State Space Models

Open paper AskPDF arXiv

With the proliferation of AI-generated content, sophisticated multimedia manipulation has raised critical concerns about malicious applications such as opinion manipulation and evidence fabrication, making Audio-Visual Temporal Forgery Localization (AV-TFL) an urgent research frontier. Existing TFL methods have progressed along two main paradigms: Transformer-based temporal modeling and channel-wise multimodal fusion. While these approaches capture temporal dependencies and cross-modal correlations, they process all frequency components indiscriminately, leading to overfitting on high-frequency noise and limited robustness under real-world data degradation. Through systematic frequency domain analysis, we find that forgery-discriminative patterns concentrate in the low/mid-frequency range (normalized frequency 0-0.15), while high-frequency components primarily introduce noise, removing them even improves detection performance by +1.4%. Based on this phenomenon, we propose UniSkip-Mamba, a frequency-aware State Space Model framework that incorporates Unified Multimodal Sequence Fusion to preserve cross-modal phase relationships, and Skip-Scanning Mamba Blocks that implement frequency-aware regularization through a novel Group-Scan-Merge mechanism, naturally biasing learning toward discriminative low/mid-frequency patterns (0-0.15) while maintaining representational completeness. We achieve state-of-the-art (SOTA) performance: 63.4% [email protected] on LAV-DF (+9.8% improvement) and 63.58% mAP on AV-Deepfake1M (+14.32% improvement), with 6x faster inference. Our frequency-domain analysis provides theoretical justification from a signal processing perspective for why skip-scanning inherently improves both accuracy and robustness.