Abstract
Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments within videos or audio streams, providing interpretable evidence for multimedia forensics and security. While most existing TFL methods rely on dense frame-level labels in a fully supervised manner, Weakly Supervised TFL (WS-TFL) reduces labeling cost by learning only from binary video-level labels. However, current WS-TFL approaches suffer from mismatched training and inference objectives, limited supervision from binary labels, gradient blockage caused by non-differentiable top-k aggregation, and the absence of explicit modeling of inter-proposal relationships. To address these issues, we propose GEM-TFL (Graph-based EM-powered Temporal Forgery Localization), a two-phase classification-regression framework that effectively bridges the supervision gap between training and inference. Built upon this foundation, (1) we enhance weak supervision by reformulating binary labels into multi-dimensional latent attributes through an EM-based optimization process; (2) we introduce a training-free temporal consistency refinement that realigns frame-level predictions for smoother temporal dynamics; and (3) we design a graph-based proposal refinement module that models temporal-semantic relationships among proposals for globally consistent confidence estimation. Extensive experiments on benchmark datasets demonstrate that GEM-TFL achieves more accurate and robust temporal forgery localization, substantially narrowing the gap with fully supervised methods.
Abstract (translated)
时间伪造定位（TFL）旨在精确识别视频或音频流中的篡改片段，为多媒体取证和安全提供可解释的证据。虽然大多数现有的TFL方法依赖于密集的关键帧标签进行全面监督学习，弱监督时间伪造定位（WS-TFL）通过仅从二进制级视频标签中学习来降低标注成本。然而，当前的WS-TFL方法面临着训练与推理目标不匹配、来自二元标签的有限指导、由非可微分top-k聚合引起的梯度阻塞以及缺乏显式的提议间关系建模的问题。 为了解决这些问题，我们提出了GEM-TFL（基于图和期望最大化的时间伪造定位），这是一种两阶段分类-回归框架，有效地弥合了训练与推理之间的监督差距。在此基础上： 1. 我们通过基于EM的优化过程将二进制标签重构成多维潜在属性，以增强弱监督； 2. 我们引入了一种无需训练的时间一致性细化方法，重新对齐帧级预测以获得更平滑的时间动态变化； 3. 我们设计了一个图基提议细化模块，通过建模提议之间的时空关系来进行全局一致的置信度估计。 在基准数据集上的广泛实验表明，GEM-TFL实现了更加准确和鲁棒的时间伪造定位，并且大大缩小了与全监督方法之间的差距。
URL
https://arxiv.org/abs/2603.05095
