We present a method for discovering patterns of activation observed through fMRI in experiments with multiple stimuli/tasks. We introduce an explicit parameterization for the profi...
Danial Lashkari, Ed Vul, Nancy Kanwisher, Polin...
When assessing reported classification results based on selection of members from a database (e.g. a face database), one would like to know what is an achievable classification ra...
This paper describes a viewpoint invariant learningbased method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal wit...
Content-based image retrieval (CBIR) addresses the problem of finding images relevant to the users' information needs, based principally on low-level visual features for whic...
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...