The existing methods for offline training of cascade classifiers take a greedy search to optimize individual classifiers in the cascade, leading inefficient overall performance. W...
In this paper, we present a learning procedure called probabilistic boosting network (PBN) for joint real-time object detection and pose estimation. Grounded on the law of total p...
Jingdan Zhang, Shaohua Kevin Zhou, Leonard McMilla...
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and explo...
In this paper, we propose an unsupervised approach to select representative face samples (models) from raw videos and build an appearance-based face recognition system. The approa...