We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient cont...
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...
In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that ...
Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...