In this paper, we propose a novel method for rapid feature space Maximum Likelihood Linear Regression (FMLLR) speaker adaptation based on bilinear models. When the amount of adapt...
This paper presents a novel classification/ retrieval system for motion events based on a perfect view invariant representation of motion trajectories and a linear classifier al...
Eser Ustunel, Xu Chen, Dan Schonfeld, Ashfaq A. Kh...
Although lots of works have been engaged in interactive and realistic rendering of translucent materials, efficient processing for deformable models remains a challenging problem...
Yi Gong, Wei Chen, Long Zhang, Yun Zeng, Qunsheng ...
Abstract. Applying real-time segmentation is a major issue when processing every frame of image sequences. In this paper, we propose a modification of the well known graph-cut algo...
Tobi Vaudrey, Daniel Gruber, Andreas Wedel, Jens K...
In this study, we suggest a method to adapt an image retrieval system into a configurable one. Basically, original feature space of a content-based retrieval system is nonlinearly...