This paper describes a method for finding wide-baseline correspondences between images at locations along gradient edges. We find edges in scale space using established methods an...
We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, whi...
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...
This article is concerned with on-line counting of harmful insects of certain species in videos in the framework of in situ video-surveillance that aims at the early detection of ...
For purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, th...