Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Straightforward classification using kernelized SVMs requires evaluating the kernel for a test vector and each of the support vectors. For a class of kernels we show that one can ...
This paper presents a new method to increase the quality of 3D video, a new media developed to represent 3D objects in motion. This representation is obtained from multi-view reco...
We address the problem of tracking and recognizing faces in real-world, noisy videos. We track faces using a tracker that adaptively builds a target model reflecting changes in ap...
Minyoung Kim, Sanjiv Kumar, Vladimir Pavlovic, Hen...
Matching articulated shapes represented by voxel-sets reduces to maximal sub-graph isomorphism when each set is described by a weighted graph. Spectral graph theory can be used to...
Diana Mateus, Radu Horaud, David Knossow, Fabio Cu...