5 papers
STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection
Jakub Micorek, Mateusz Koziński, Horst Possegger
Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving…
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
Jakub Micorek, Horst Possegger, Dominik Narnhofer +2
We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this…
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin +5
Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language M…
Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Stefan Leitner, M. Jehanzeb Mirza, Wei Lin +5
In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when te…
The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
M. Jehanzeb Mirza, Jakub Micorek, Horst Possegger +1
Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of l…