We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the...
We propose to use high-level visual information to improve illuminant estimation. Several illuminant estimation approaches are applied to compute a set of possible illuminants. Fo...
Joost van de Weijer, Cordelia Schmid, Jakob J. Ver...
Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extended occlusion whe...
Neel Joshi, Shai Avidan, Wojciech Matusik, David J...
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feed...
Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Po...
This paper discusses building complex classifiers from a single labeled example and vast number of unlabeled observation sets, each derived from observation of a single process or...