Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jeong, Sungheon, Park, Jihong, Imani, Mohsen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909604310417408
author Jeong, Sungheon
Park, Jihong
Imani, Mohsen
author_facet Jeong, Sungheon
Park, Jihong
Imani, Mohsen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02393
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection
Jeong, Sungheon
Park, Jihong
Imani, Mohsen
Computer Vision and Pattern Recognition
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.
title Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.02393