While great strides have been made in detecting and localizing specific objects in natural images, the bottom-up segmentation of unknown, generic objects remains a difficult chall...
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally par...
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...
In this work we present Discriminative Random Fields (DRFs), a discriminative framework for the classification of image regions by incorporating neighborhood interactions in the l...
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...