DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization
This work provides a more precise and efficient method for identifying manipulated segments in video and audio, which is crucial for security and forensics applications.
This paper addresses the challenge of Temporal Forgery Localization (TFL) in video and audio by proposing DeformTrace, a novel State Space Model (SSM) architecture. DeformTrace enhances SSMs with deformable dynamics and relay mechanisms, achieving state-of-the-art performance with fewer parameters and faster inference.
Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal reasoning, their use in TFL is hindered by ambiguous boundaries, sparse forgeries, and limited long-range modeling. We propose DeformTrace, which enhances SSMs with deformable dynamics and relay mechanisms to address these challenges. Specifically, Deformable Self-SSM (DS-SSM) introduces dynamic receptive fields into SSMs for precise temporal localization. To further enhance its capacity for temporal reasoning and mitigate long-range decay, a Relay Token Mechanism is integrated into DS-SSM. Besides, Deformable Cross-SSM (DC-SSM) partitions the global state space into query-specific subspaces, reducing non-forgery information accumulation and boosting sensitivity to sparse forgeries. These components are integrated into a hybrid architecture that combines the global modeling of Transformers with the efficiency of SSMs. Extensive experiments show that DeformTrace achieves state-of-the-art performance with fewer parameters, faster inference, and stronger robustness.