Reconstructing the full contour of the tongue from the position of 3 to 4 landmarks on it is useful in articulatory speech work. This can be done with submillimetric accuracy usin...
We present a new phone-dependent feature weighting scheme that can be used to map articulatory configurations (e.g. EMA) onto vocal tract spectra (e.g. MFCC) through table lookup....
Daniel Felps, Christian Geng, Michael Berger, Kori...
Abstract— We propose a novel hierarchical structured prediction approach for ranking images of faces based on attributes. We view ranking as a bipartite graph matching problem; l...
Despite significant recent progress, the best available visual saliency models still lag behind human performance in predicting eye fixations in free-viewing of natural scenes. ...
Abstract. The expected economic impact of new health enabling technologies is often used as motivation for their development. Another motivation is the predicted positive impact on...