In real life, visual learning is supposed to be a continuous process. Humans have an innate facility to recognize objects even under less-than-ideal conditions and to build robust ...
In this paper, we describe completed and ongoing work towards an interactive multimedia system that will appeal to today’s youth culture identified as most likely to adopt such ...
Many learning tasks for computer vision problems can be described by multiple views or multiple features. These views can be exploited in order to learn from unlabeled data, a.k.a....
Abstract Research in the field of sign language recognition has made significant advances in recent years. The present achievements provide the basis for future applications with t...
This paper presents a new photometric stereo method aiming to efficiently estimate BRDF and reconstruct glossy surfaces. Rough specular surfaces exhibit wide specular lobes under ...