A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Winner-Takes-All (WTA) prescriptions for Learning Vector Quantization (LVQ) are studied in the framework of a model situation: Two competing prototype vectors are updated accordin...
Face recognition (FR) is an active yet challenging topic in computer vision applications. As a powerful tool to represent high dimensional data, recently sparse representation bas...
We present a probabilistic model for clustering of objects represented via pairwise dissimilarities. We propose that even if an underlying vectorial representation exists, it is b...
Julia E. Vogt, Sandhya Prabhakaran, Thomas J. Fuch...
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...