Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection
This work addresses the problem of detecting anomalies in videos for applications like surveillance, offering a robust solution that improves accuracy by leveraging motion cues often missed in RGB frames, though it is incremental in its multimodal fusion approach.
The paper tackled video anomaly detection by proposing a framework that fuses synthetic event representations with image features using uncertainty-aware methods, achieving new state-of-the-art results on multiple benchmarks without needing dedicated event sensors or frame-level labels.
Most existing video anomaly detectors rely solely on RGB frames, which lack the temporal resolution needed to capture abrupt or transient motion cues, key indicators of anomalous events. To address this limitation, we propose Image-Event Fusion for Video Anomaly Detection (IEF-VAD), a framework that synthesizes event representations directly from RGB videos and fuses them with image features through a principled, uncertainty-aware process. The system (i) models heavy-tailed sensor noise with a Student`s-t likelihood, deriving value-level inverse-variance weights via a Laplace approximation; (ii) applies Kalman-style frame-wise updates to balance modalities over time; and (iii) iteratively refines the fused latent state to erase residual cross-modal noise. Without any dedicated event sensor or frame-level labels, IEF-VAD sets a new state of the art across multiple real-world anomaly detection benchmarks. These findings highlight the utility of synthetic event representations in emphasizing motion cues that are often underrepresented in RGB frames, enabling accurate and robust video understanding across diverse applications without requiring dedicated event sensors. Code and models are available at https://github.com/EavnJeong/IEF-VAD.