This paper presents an unsupervised learning approach to video-based face recognition that does not make any assumptions about the pose, expressions or prior localization of landm...
Abstract. Increasing risks of spoof attacks and other common problems of unimodal biometric systems such as intra-class variations, nonuniversality and noisy data necessitate the u...
Syed M. S. Islam, Mohammed Bennamoun, Ajmal S. Mia...
An application for content-based annotation and retrieval of videos can be found in the sport domain, where videos are annotated in order to produce short summaries for news and sp...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
We present a novel approach to address the representation issue and the matching issue in face recognition (verification). Firstly, our approach encodes the micro-structures of t...