We address the problem of multi-person dataassociation-based tracking (DAT) in semi-crowded environments from a single camera. Existing trackletassociation-based methods using pur...
We present a novel method for analyzing social behavior. Continuous videos are segmented into action ‘bouts’ by building a temporal context model that combines features from s...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Most tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework called Hidden Markov Model, where the distribution of the object state a...
Most current 3D face recognition algorithms are designed based on the data collected in controlled situations, which leads to the un-guaranteed performance in practical systems. I...