Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...
Yuya Akita, Masato Mimura, Graham Neubig, Tatsuya ...
Recently, supervised dimensionality reduction has been gaining attention, owing to the realization that data labels are often available and indicate important underlying structure...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
Abstract. We propose a method for atrophy simulation in structural MR images based on finite-element methods, providing data for objective evaluation of atrophy measurement techniq...
Oscar Camara-Rey, Martin Schweiger, Rachael I. Sca...
Abstract. This paper is about the evaluation of the results of clustering algorithms, and the comparison of such algorithms. We propose a new method based on the enrichment of a se...