An autoencoder with minimal latent entropy loss enables fully unsupervised video anomaly detection by concentrating normal latent embeddings and producing poor reconstructions for anomalies.
In: Proceedings of the IEEE conference on computer vision and pattern recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CoReVAD applies a single frozen VLM with local response cleaning and temporal refinement steps to deliver competitive training-free video anomaly detection plus explanations on UCF-Crime and XD-Violence.
citing papers explorer
-
MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection
An autoencoder with minimal latent entropy loss enables fully unsupervised video anomaly detection by concentrating normal latent embeddings and producing poor reconstructions for anomalies.
-
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
CoReVAD applies a single frozen VLM with local response cleaning and temporal refinement steps to deliver competitive training-free video anomaly detection plus explanations on UCF-Crime and XD-Violence.