We propose a novel learning algorithm to detect moving pedestrians from a stationary camera in real-time. The algorithm learns a discriminative model based on eigenflow, i.e. the ...
Background subtraction is an essential task in several static camera based computer vision systems. Background modeling is often challenged by spatio-temporal changes occurring due...
Prithwijit Guha, Dibyendu Palai, K. S. Venkatesh, ...
Latest results of statistical learning theory have provided techniques such us pattern analysis and relational learning, which help in modeling system behavior, e.g. the semantics ...
Abstract—We describe a novel application of using data mining and statistical learning methods to automatically monitor and detect abnormal execution traces from console logs in ...
Wei Xu, Ling Huang, Armando Fox, David Patterson, ...
Currently, video analysis algorithms suffer from lack of information
regarding the objects present, their interactions,
as well as from missing comprehensive annotated video
dat...
Jenny Yuen, Bryan Russell, Ce Liu, Antonio Torralb...