We present a new scheme to robustly detect a type of human attentive behavior, which we call frequent change in focus of attention (FCFA), from video sequences. FCFA behavior can b...
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...
Markov random field (MRF) models, including conditional random field models, are popular in computer vision. However, in order to be computationally tractable, they are limited to ...