We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Automatically understanding human actions from video sequences is a very challenging problem. This involves the extraction of relevant visual information from a video sequence, re...
Volume rendering is a valuable and important technique for scientific visualization. One well known application area is the reconstruction and visualization of output from medica...
Roger C. Tam, Christopher G. Healey, Borys Flak, P...
Modeling system performance and workload characteristics has become essential for efficiently provisioning Internet services and for accurately predicting future resource requirem...
We present an approach for measuring similarity between visual entities (images or videos) based on matching internal self-similarities. What is correlated across images (or acros...