A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation
Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision.
ProofPaper ↗
Key points
- Recent generative approaches detect anomalies from a distributional perspective, but remain limited by local anomaly modes.
- Meanwhile, video anomaly anticipation (VAA), as a proactive extension beyond post-hoc detection, introduces additional challenges.
- To address these challenges, we propose a unified score-driven framework, termed Uni-DSM, based on denoising score matching (DSM), which models anomaly patterns through likelihood estimation and score functions over the learned data distribution.
- For VAD, we instantiate an autoregressive denoising score matching (ADSM) mechanism, which progressively accumulates anomalous evidence via autoregressive denoising, enabling enhanced perception of local modes beyond visual cues.
Sources (1)
- [1]A Unified Score Matching Paradigm for Video Anomaly Detection and AnticipationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 03:12 AM
Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision.
Recent generative approaches detect anomalies from a distributional perspective, but remain limited by local anomaly modes.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- Oct 7, 2026MotherTree: Meta-learning on synthetic data improves decision tree training
- Oct 7, 2026Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
- Oct 6, 2026Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity
- Oct 6, 2026EmbeddingGemma 2: an open, lightweight multimodal embedding model
- Oct 6, 2026Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images