This paper presents a new criterion for viewpoint selection in the context of active Bayesian object recognition and pose estimation. Recognition is performed by probabilistically...
We present a pattern recognizer to classify a variety of objects and their pose on a table from real world images. Learning of weights in a linear discriminant is based on estimat...
This paper addresses the problem of recovering 3D human pose from a single monocular image, using a discriminative bag-of-words approach. In previous work, the visual words are le...
Huazhong Ning, Wei Xu, Yihong Gong, Thomas S. Huan...
Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. Howeve...
Detecting objects in cluttered scenes and estimating articulated human body parts are two challenging problems in computer vision. The difficulty is particularly pronounced in ac...