Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Occlusion and lack of visibility in dense crowded scenes make it very difficult to track individual people correctly and consistently. This problem is particularly hard to tackle i...
A novel adaptive and patch-based approach is proposed for image regularization and representation. The method is unsupervised and based on a pointwise selection of small image patc...
Belief propagation (BP) has become widely used for low-level vision problems and various inference techniques have been proposed for loopy graphs. These methods typically rely on a...
Xiangyang Lan, Stefan Roth, Daniel P. Huttenlocher...
Abstract. Human faces are remarkably similar in global properties, including size, aspect ratios, and locations of main features, but can vary considerably in details across indivi...
Abstract. We present a geometric and statistical approach to gaitbased human recognition. The novelty here is to consider observations of gait, considered as planar silhouettes, to...
This paper introduces the Located Hidden Random Field (LHRF), a conditional model for simultaneous part-based detection and segmentation of objects of a given class. Given a traini...
Abstract. In order to reconstruct 3-D Euclidean shape by the TomasiKanade factorization, one needs to specify an affine camera model such as orthographic, weak perspective, and par...
Ken-ichi Kanatani, Yasuyuki Sugaya, Hanno Ackerman...
Local appearance models in the neighborhood of salient image features, together with local and/or global geometric constraints, serve as the basis for several recent and effective...
Generalized Belief Propagation (gbp) has proven to be a promising technique for performing inference on Markov random fields (mrfs). However, its heavy computational cost and large...