In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
Ming Li, Sanqing Hu, Shih-Hsi Liu, Sung Baang, Yu ...
This paper presents a new normalcy model of a scene for change detection using images taken from multiple views and varying illumination conditions. Each coregistered pixel site i...
David B. Cooper, Joseph L. Mundy, Osman Gokhan Sez...
In this work we describe a technique to calibrate images for skin analysis in dermatology. Using a common reference we correct non-uniform illumination effects, give an estimation...
Costantino Grana, Giovanni Pellacani, Stefania Sei...
In this paper, we propose a novel classification method, called nearest intra-class space (NICS), for face recognition. In our method, the distribution of face patterns of each pe...
We propose a method for extracting a gaze region from an observed image by analyzing human's view directions and image information. The view direction of the user, which is r...