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 propose a new unsupervised learning method to obtain a layered pictorial structure (LPS) representation of an articulated object from video sequences. It will be seen that this...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
We consider a variation of the problem of combining expert opinions for the situation in which there is no ground truth to use for training. Even though we don’t have labeled da...
Sharath R. Cholleti, Sally A. Goldman, Avrim Blum,...
In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to...
Andrew Rabinovich, Andrea Vedaldi, Carolina Galleg...
People identification is an essential task for video content analysis in a surveillance system. A good classifier, however, requires a large amount of training data, which may not...