Abstract. We present a comparative study on how to use discriminative learning methods such as classification, regression, and ranking to address deformable shape segmentation. Tra...
Jingdan Zhang, Shaohua Kevin Zhou, Dorin Comaniciu...
Abstract. In this paper, we propose a novel method for the unsupervised clustering of graphs in the context of the constellation approach to object recognition. Such method is an E...
Boyan Bonev, Francisco Escolano, Miguel Angel Loza...
Human activity analysis is an important problem in computer
vision with applications in surveillance and summarization
and indexing of consumer content. Complex human
activities...
Abstract. There has been growing interest in practice in using unlabeled data together with labeled data in machine learning, and a number of different approaches have been develo...
In many image retrieval applications, the mapping between highlevel semantic concept and low-level features is obtained through a learning process. Traditional approaches often as...