We present a data-mining experiment on feature selection for automatic emotion recognition. Starting from more than 1000 features derived from pitch, energy and MFCC time series, ...
The power consumption of video enabled mobile devices is an ongoing challenge. The computational burden caused by the motion estimation process involved in video compression is th...
We propose a method for generating a dynamic lecture video from the high resolution images recorded by a HDV camcorder. The lecture images are cropped to track the region of the i...
We propose to use a visual object (e.g., the baseball catcher) detection algorithm to find local, semantic objects in video frames in addition to an audio classification algorit...
We present the ZoomSlider, a new interface for skimming and browsing video content in a flexible and interactive way. It circumvents common problems of existing video browsing app...