This paper presents a novel paradigm for learning languages that consists of mapping strings to an appropriate high-dimensional feature space and learning a separating hyperplane i...
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping ha...
We consider the following Tree-Constrained Bipartite Matching problem: Given two rooted trees T1 = (V1, E1), T2 = (V2, E2) and a weight function w : V1 × V2 → R+, find a maximu...
Stefan Canzar, Khaled M. Elbassioni, Gunnar W. Kla...
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their traini...