Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
Biomedical images and captions are one of the major sources of information in online biomedical publications. They often contain the most important results to be reported, and pro...
Xin Chen, Caimei Lu, Yuan An, Palakorn Achananupar...
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Anticipating the availability of large questionanswer datasets, we propose a principled, datadriven Instance-Based approach to Question Answering. Most question answering systems ...