Jamie Shotton

TL;DR: In this article, the authors proposed an algorithm that matches a non-photorealistic, synthetically generated image to a latent vector of a pretrained StyleGAN2 model which, in turn, maps the vector to a photorealistic image of a person of the same pose, expression, hair, and lighting.

TL;DR: In this paper, a user interface comprises a display controller configured to render graphical data on a display, and a memory configured to receive captured sensor data depicting at least one hand of a user operating the user interface without touching the interface.

TL;DR: In this paper, a multi-centroid compression for probability distribution clouds is proposed, where a centroid is generated for each cluster, which usually results for a plurality of centroids for each distinguished object.

TL;DR: Using high-level attributes to guide image processing is described in this article, where one or more random decision forests are trained using images where global variable values such as player height are known in addition to ground-truth data appropriate for the image processing task concerned.

TL;DR: The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) as discussed by the authors was organized in conjunction with the MICCAI 2012 and 2013 conferences, and twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low and high grade glioma patients.