Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
While video-based activity analysis and recognition has received much attention, existing body of work mostly deals with single object/person case. Coordinated multi-object activi...
Visual tracking is a challenging problem, as an object may change its appearance due to pose variations, illumination changes, and occlusions. Many algorithms have been proposed t...
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 ...