We present an efficient probabilistic method for identity recognition in personal photo albums. Personal photos are usually taken under uncontrolled conditions ? the captured face...
Previous pixel-level change detection methods either contain a background updating step that is costly for moving cameras (background subtraction) or can not locate object positio...
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous se...
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and explo...
Image segmentation plays an important role in computer vision and image analysis. In this paper, the segmentation problem is formulated as a labeling problem under a probability m...