Traditional Naive Bayes Classifier performs miserably on web-scale taxonomies. In this paper, we investigate the reasons behind such bad performance. We discover that the low perf...
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
We propose a novel directed graphical model for label propagation in lengthy and complex video sequences. Given hand-labelled start and end frames of a video sequence, a variation...
Ignas Budvytis, Vijay Badrinarayanan, Roberto Cipo...
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
Data visualization plays a crucial role in identifying interesting patterns in exploratory data analysis. Its use is, however, made difficult by the large number of possible data p...