This paper describes a method for recognizing partially occluded objects under different levels of illumination brightness by using the eigenspace analysis. In our previous work, w...
A key ingredient in the design of visual object classification
systems is the identification of relevant class specific
aspects while being robust to intra-class variations. Whil...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
This paper is about the use of metric data structures in high-dimensionalor non-Euclidean space to permit cached sufficientstatisticsaccelerationsof learning algorithms. It has re...
We propose a method that detects and segments multiple, partially occluded objects in images. A part hierarchy is defined for the object class. Whole-object segmentor and part de...