Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Yue, Li, Jingjing, Lu, Qijia, Ji, Wei, Zhang, Jingrou, Shen, Fei, Li, Xiao, Jia, Yizhen, Chen, Qiang, Wang, Limin, Li, Wentong, Qin, Jie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917556129890304
author Feng, Yue
Li, Jingjing
Lu, Qijia
Ji, Wei
Zhang, Jingrou
Shen, Fei
Li, Xiao
Jia, Yizhen
Chen, Qiang
Wang, Limin
Li, Wentong
Qin, Jie
author_facet Feng, Yue
Li, Jingjing
Lu, Qijia
Ji, Wei
Zhang, Jingrou
Shen, Fei
Li, Xiao
Jia, Yizhen
Chen, Qiang
Wang, Limin
Li, Wentong
Qin, Jie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2606_02402
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Feng, Yue
Li, Jingjing
Lu, Qijia
Ji, Wei
Zhang, Jingrou
Shen, Fei
Li, Xiao
Jia, Yizhen
Chen, Qiang
Wang, Limin
Li, Wentong
Qin, Jie
Computer Vision and Pattern Recognition
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.
title Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.02402