This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the ...
We present a new variational level-set-based segmentation
formulation that uses both shape and intensity prior information
learned from a training set. By applying Bayes’
rule...
Training a classifier for object category recognition using images on the Internet is an attractive approach due to its scalability. However, a big challenge in this approach is ...
In this paper, a novel and efficient automatic image categorization system is proposed. This system integrates the MIL-based and global-featurebased SVMs for categorization. The IP...
Learning to understand a single causal system can be an achievement, but humans must learn about multiple causal systems over the course of a lifetime. We present a hierarchical B...
Charles Kemp, Noah D. Goodman, Joshua B. Tenenbaum