Latent Clarity: Bridging World-Model Kinematics to Semantic Manifolds for Video Anomaly Anticipation

Continuous video anomaly detection is dominated by reactive Multiple Instance Learning (MIL) that collapses spatiotemporal features into scalar scores.

Continuous video anomaly detection is dominated by reactive Multiple Instance Learning (MIL) that collapses spatiotemporal features into scalar scores. We introduce PULS (Predictive Unified Latent Space), a continuous semantic world-model pipeline comprising two modules: a…