We develop a method to detect erroneous interpretation results of user utterances by exploiting utterance histories of individual users in spoken dialogue systems that were deploy...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
While supervised learning approaches for 3D shape retrieval have been successfully used to incorporate human knowledge about object classes based on global shape features, the inc...
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
Segmentation of video objects from background is a popular computer vision problem and has many important applications. Most existing methods are either computationally expensive ...