DDNet: A Dual-Stream Graph Learning and Disentanglement Framework for Temporal Forgery Localization

TL;DR

DDNet is a novel dual-stream graph learning framework that effectively localizes video forgeries by capturing both local artifacts and global semantic cues, outperforming existing methods.

Contribution

The paper introduces DDNet, combining local and global analysis with disentanglement and feature fusion techniques for improved temporal forgery localization.

Findings

Outperforms state-of-the-art by ~9% AP@0.95

Enhances cross-domain robustness in forgery detection

Effectively isolates generic forgery fingerprints

Abstract

The rapid evolution of AIGC technology enables misleading viewers by tampering mere small segments within a video, rendering video-level detection inaccurate and unpersuasive. Consequently, temporal forgery localization (TFL), which aims to precisely pinpoint tampered segments, becomes critical. However, existing methods are often constrained by \emph{local view}, failing to capture global anomalies. To address this, we propose a \underline{d}ual-stream graph learning and \underline{d}isentanglement framework for temporal forgery localization (DDNet). By coordinating a \emph{Temporal Distance Stream} for local artifacts and a \emph{Semantic Content Stream} for long-range connections, DDNet prevents global cues from being drowned out by local smoothness. Furthermore, we introduce Trace Disentanglement and Adaptation (TDA) to isolate generic forgery fingerprints, alongside Cross-Level Feature Embedding (CLFE) to construct a robust feature foundation via deep fusion of hierarchical features. Experiments on ForgeryNet and TVIL benchmarks demonstrate that our method outperforms state-of-the-art approaches by approximately 9\% in AP@0.95, with significant improvements in cross-domain robustness.