Automatic audio event recognition plays a pivotal role in making human robot interaction
more closer and has a wide applicability in industrial automation, control and surveillance …

This paper proposes an efficient feature sampling and multi-task learning scheme for traffic
scene analysis, where all classifiers are trained simultaneously by exploiting the correlations …

We propose a novel feature based on optical flow for action recognition. The feature is quite
simple and has much lower computational load than the existing features for action …

Background Uncovering the hidden organizational characteristics and regularities among
biological sequences is the key issue for detailed understanding of an underlying biological …

We propose the proximity clustering (PxC) algorithm, which finds the spatially diverse but
semantically similar data-point colonies in the form of a dominant class cluster. It searches …

A method is presented to the discrimination, extraction and reconstruction of human
behavior in the area forbidden by high voltage, in particular, a method of scene reproduction …

Interstellar, satellite and microscopic imaging methods produce high-resolution images
which carry vital information even at a pixel level. Translucent hindrance from reflection …