The complexity of pedestrian spatio-temporal behaviour calls for the combination of several complementary empirical methods in order to comprehensively understand human motion beha...
—In this work we propose a dynamic-texture-based approach to the recognition of facial Action Units (AUs, atomic facial gestures) and their temporal models (i.e., sequences of te...
Acoustic event detection (AED) aims to identify both timestamps and types of multiple events and has been found to be very challenging. The cues for these events often times exist...
Po-Sen Huang, Xiaodan Zhuang, Mark Hasegawa-Johnso...
Straightforward classification using kernelized SVMs requires evaluating the kernel for a test vector and each of the support vectors. For a class of kernels we show that one can ...
For detecting objects in natural visual scenes, several powerful image features have been proposed which can collectively be described as spatial histograms of oriented energy. Th...