Many computer vision problems can be formulated in
a Bayesian framework with Markov Random Field (MRF)
or Conditional Random Field (CRF) priors. Usually, the
model assumes that ...
Object tracking typically relies on a dynamic model to
predict the object’s location from its past trajectory. In
crowded scenarios a strong dynamic model is particularly
impo...
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
We develop an automatic system to analyze subtle changes in upper face expressions based on both permanent facial features (brows, eyes, mouth)andtransient facial features (deepen...
We present a novel approach for tracking locally planar regions in an image sequence and their grouping into larger planar surfaces. The tracker recovers the affine transformation...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...