We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
Due to the intrinsic subtlety and dynamics of eye movements, automated generation of natural and engaging eye motion has been a challenging task for decades. In this paper we pres...
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
A video sequence of an underwater scene taken from
above the water surface suffers from severe distortions due
to water fluctuations. In this paper, we simultaneously estimate
t...
The paper proposes a method to keep the tracker robust to background clutters by online selecting discriminative features from a large feature space. Furthermore, the feature sele...