Many diagrams contain compound objects composed of parts. We propose a recognition framework that learns parts in an unsupervised way, and requires training labels only for compou...
Recently, sparse coding has been receiving much attention in object and scene recognition tasks because of its superiority in learning an effective codebook over k-means clusterin...
This paper gives the SNAP and SPAN ontologies relating to recognizing variable vista spatial environments, namely, SNAPVis and SPANVis. It proposes that recognizing spatial environ...
We introduce a new metaphor for learning spatial relations--the 3D puzzle. With this metaphor users learn spatial relations by assembling a geometric model themselves. For this pu...
Bernhard Preim, Felix Ritter, Oliver Deussen, Thom...
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...