This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
Non-negative tensor factorization (NTF) has recently been proposed as sparse and efficient image representation (Welling and Weber, Patt. Rec. Let., 2001). Until now, sparsity of t...
Abstract. Two new techniques based on nonparametric estimation of probability densities are introduced which improve on the performance of equivalent robust methods currently emplo...
Any real-time interactive video coding algorithm used over the Internet needs to be able to cope with packet loss, since the existing error recovery mechanisms are not suitable fo...
This paper presents an approach to estimating the parameters of continuous density HMMs for visual speech recognition. One of the key issues of image-based visual speech recogniti...