Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
: In this paper we discuss theoretical foundations and a practical realization of a real-time traffic sign detection, tracking and recognition system operating on board of a vehicl...
Andrzej Ruta, Fatih Porikli, Shintaro Watanabe, Yo...
ons for this project. Most recent ones are listed at the end of this abstract. In the future, feature selection will be integrated in the multi-class EM algorithm to improve the pe...
Conventional subspace learning or recent feature extraction methods consider globality as the key criterion to design discriminative algorithms for image classification. We demonst...
Yun Fu, Zhu Li, Junsong Yuan, Ying Wu, Thomas S. H...
As digital cameras with Global Positioning System (GPS) capability become available and people geotag their photos using other means, it is of great interest to annotate semantic e...