Training of conditional random fields often takes the form of a double-loop procedure with message-passing inference in the inner loop. This can be very expensive, as the need to...
In this paper we propose a novel approach to content-based image retrieval with relevance feedback, which is based on the random walker algorithm introduced in the context of inte...
Variational relaxations can be used to compute approximate minimizers of optimal partitioning and multiclass labeling problems on continuous domains. While the resulting relaxed co...
“Energy” models for continuous domains can be applied to many problems, but often suffer from high computational expense in training, due to the need to repeatedly minimize t...
Abstract. Issues related to 3d turtle’s navigation and geometrical figures’ manipulation in the simulated 3d space of a newly developed computational environment, MaLT, are re...