In this paper, we propose an online motion capture marker labeling approach for multiple interacting articulated targets. Given hundreds of unlabeled motion capture markers from m...
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic ...
This paper is an enquiry into the interaction between multiple description coding (MDC) and network routing. We are mainly concerned with rate-distortion optimized network flow of...
We present a new approach to appearance-based object recognition, which captures the relationships between multiple model views and exploits them to improve recognition performanc...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
This paper proposes an algorithm to simultaneously estimate both the 3D shape and parameters of a surface reflectance model from multiple views of an object made of a single mater...