We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Effective access to and navigation in information stored in deep Web ontological repositories or relational databases has yet to be realized due to issues with usability of user i...
Computers have been widely deployed to our daily lives, but human-computer interaction still lacks intuition. Researchers intend to resolve these shortcomings by augmenting tradit...
Matthias Wimmer, Christoph Mayer, Sylvia Pietzsch,...
Phoneme segmentation is a fundamental problem in many speech recognition and synthesis studies. Unsupervised phoneme segmentation assumes no knowledge on linguistic contents and a...
Discovering human disease-causing genes (disease genes in short) is one of the most challenging problems in bioinformatics and biomedicine, as most diseases are related in some wa...