We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should ...
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 learning-based hierarchical approach of multi-target tracking from a single camera by progressively associating detection responses into longer and longer track fragm...
Generative topic models such as LDA are limited by their inability to utilize nontrivial input features to enhance their performance, and many topic models assume that topic assig...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...