Computer vision tasks such as learning, recognition, classification or segmentation applied to spatial data often requires spatial normalization of repeated features and structure...
We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
The goal of this work is to automatically learn a large
number of British Sign Language (BSL) signs from TV
broadcasts. We achieve this by using the supervisory information
avai...
Patrick Buehler (University of Oxford), Mark Everi...
Many applications in computer vision and pattern recognition involve drawing inferences on certain manifoldvalued parameters. In order to develop accurate inference algorithms on ...
Pavan K. Turaga, Ashok Veeraraghavan, Rama Chellap...
We propose a fast algorithm, EMD-L1, for computing the Earth Mover's Distance (EMD) between a pair of histograms. Compared to the original formulation, EMD-L1 has a largely si...