In this paper, we take the human age and pose estimation problems as examples to study automatic designing regressor from training samples with uncertain nonnegative labels. First...
Shuicheng Yan, Huan Wang, Xiaoou Tang, Thomas S. H...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
We develop an efficient learning framework to construct signal dictionaries for sparse representation by selecting the dictionary columns from multiple candidate bases. By sparse,...
We present an approach to spatial inference which is based on the procedural semantics of spatial relations. In contrast to qualitative reasoning, we do not use discrete symbolic m...
Sylvia Wiebrock, Lars Wittenburg, Ute Schmid, Frit...
An object on the Semantic Web is likely to be denoted with multiple URIs by different parties. Object coreference resolution is to identify “equivalent” URIs that denote the ...