Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
We present an Audio-visual person authentication system which extracts several novel "VisualizedSpeech-Features" (VSF) from the spoken-password and multiple face profile...
This paper extends our previous work on feature transformationbased support vector machines for speaker recognition by proposing a joint MAP adaptation of feature transformation (...
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
A formal treatment of typed feature structures (TFSs) is developed to augment TFSs, so that negative descriptions of them can be treated. Negative descriptions of TFSs can make li...