Luc Van Gool

TL;DR: The proposed interactive museum guide achieves object recognition via image matching and thus allows the use of model sets that do not need to be segmented and a postprocessing strategy that allows to improve object recognition rates by suppressing multiple matches.

TL;DR: Observers' ability to discriminate ‘same’ from ‘different’ pairs of patterns depended strongly on the position of the fourth, displaced, point: performance varied rapidly when the location of the displaced point was such that the patterns were nearly triangular or nearly parallel sided, consistent with observers using the hypothesised qualitative cues.

TL;DR: In this paper, the authors proposed to compress the whole network jointly instead of in a layer-wise manner, which provides another flexible choice for network compression because the techniques complement each other.

TL;DR: A solution for the complementary task of extracting fixed structures that remain fixed under the transformations that relate corresponding contour segments in regular patterns in an efficient and non-combinatorial way, based on the iterated application of the Hough transform.

TL;DR: This work proposes a method to model 3D MR brain volumes distribution by combining a 2D slice VAE with a Gaussian model that captures the relationships between slices and introduces a novel evaluation method for generated volumes that quantifies how well their segmentations match those of true brain anatomy.