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 p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
Labeling video data is an essential prerequisite for many vision applications that depend on training data, such as visual information retrieval, object recognition, and human act...
Capturing surface appearance is important for a large number of applications. Appearance of real world surfaces is dif?cult to model as it varies with the direction of illuminatio...
Several geometric active contour models have been proposed for segmentation in computer vision. The essential idea is to evolve a curve (in 2D) or a surface (in 3D) under constrai...
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to...