Abstract. In surveillance systems for monitoring people behaviour, it is imporant to build systems that can adapt to the signatures of the people tasks and movements in the environ...
Nam Thanh Nguyen, Svetha Venkatesh, Geoff A. W. We...
This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
Pitch mismatch between training and testing is one of the important factors causing the performance degradation of the speaker recognition system. In this paper, we adopted the mis...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semisupervised manner: the model is learnt from example ...