We investigate to what extent combinations of features can improve classification performance on a large dataset of similar classes. To this end we introduce a 103 class flower da...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
We study the problem of classifying mild Alzheimer's disease (AD) subjects from healthy individuals (controls) using multi-modal image data, to facilitate early identification...
Chris Hinrichs, Vikas Singh, Guofan Xu, Sterlin...