We propose a space-time Markov Random Field (MRF)
model to detect abnormal activities in video. The nodes in
the MRF graph correspond to a grid of local regions in the
video fra...
Jaechul Kim (University of Texas at Austin), Krist...
The increasing complexity of today’s systems makes fast and accurate failure detection essential for their use in mission-critical applications. Various monitoring methods provi...
Online learning has shown to be successful in tracking of previously unknown objects. However, most approaches are limited to a bounding-box representation with fixed aspect rati...
Novelty detection involves identifying novel patterns. They are not usually available during training. Even if they are, the data quantity imbalance leads to a low classification ...
While supervised learning approaches for 3D shape retrieval have been successfully used to incorporate human knowledge about object classes based on global shape features, the inc...