Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of detecting and explaining AI-generated fake parts inside long videos, where fake clips appear only occasionally within real footage. They create a new task called Temporal AI-Generated Segment Localization and Explanation to find exactly when and where these fake parts occur and provide understandable reasons. To support this, they build a large video dataset named TASLE and introduce a method called MSLoc that efficiently spots fake video sections and explains them clearly. Their experiments show this approach works well and that explaining fake segments is important for analyzing long videos.
AI-generated videovideo forensicstemporal localizationdeepfake detectionlong-form videosegment-level explanationdataset benchmarkmultimodal large language modelboundary-sensitive proposal
Authors
Yue Feng, Jingjing Li, Qijia Lu, Wei Ji, Jingrou Zhang, Fei Shen, Xiao Li, Yizhen Jia, Qiang Chen, Limin Wang, Wentong Li, Jie Qin
Abstract
The rapid advancement of AI-driven video generation has transformed content creation, while simultaneously increasing the risk of misinformation through localized manipulations in long-form videos. Existing video forensic methods predominantly operate on short, independent clips, and thus fail to capture realistic scenarios where AI-generated content is sparsely embedded within otherwise authentic footage. To bridge this gap, we formulate the task of Temporal AI-Generated Segment Localization and Explanation, which targets authenticity detection, temporal localization, and interpretable analysis of manipulated segments in untrimmed long videos. We further introduce TASLE, a large-scale benchmark comprising 12,472 untrimmed videos with diverse manipulation patterns and rich annotation signals, including temporal boundaries, authenticity labels, and segment-level rationales. In addition, we propose MSLoc, a coarse-to-fine forensic baseline that combines a boundary-sensitive proposal generation module for efficient long-video scanning with an MLLM-based refinement module for precise boundary localization and interpretable reasoning. Experiments validate the effectiveness of the proposed baseline, highlighting the importance of segment-level explainable forensics for long-form AI-generated video analysis. Our dataset and code are publicly available at https://debby-0527.github.io/TASLE.