This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflec...
—This paper presents a new approach for graphical symbols recognition by combining a concept lattice with a bag of words representation. Visual words define the properties of a ...
We present a novel approach to constraintbased causal discovery, that takes the form of straightforward logical inference, applied to a list of simple, logical statements about ca...
—We present an algorithm that simultaneously calibrates two color cameras, a depth camera, and the relative pose between them. The method is designed to have three key features: ...
Daniel Herrera C., Juho Kannala, Janne Heikkil&aum...
This paper proposes a data-driven method for concept-to-text generation, the task of automatically producing textual output from non-linguistic input. A key insight in our approac...