: Covariance matrices capture correlations that are invaluable in modeling real-life datasets. Using all d2 elements of the covariance (in d dimensions) is costly and could result ...
In this paper, we propose an approach to learning appearance models of moving objects directly from compressed video. The appearance of a moving object changes dynamically in vide...
We present the IBM systems for the Rich Transcription 2007 (RT07) speaker diarization evaluation task on lecture meeting data. We first overview our baseline system that was devel...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
The performance of graph based clustering methods critically depends on the quality of the distance function, used to compute similarities between pairs of neighboring nodes. In t...