Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we sh...
We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific an...
Given a dense set of imperfect normals obtained by photometric stereo or shape from shading, this paper presents an optimization algorithm which alternately optimizes until conver...
Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essent...
Shengyang Dai, Ming Yang, Ying Wu, Aggelos K. Kats...
We propose a first attempt to classify events in static images by integrating scene and object categorizations. We define an event in a static image as a human activity taking pla...