Andrew Zisserman

TL;DR: A comprehensive public dataset, NightOwls, is introduced, for pedestrian detection at night, due to variable and low illumination, reflections, blur, and changing contrast in comparison to daytime conditions.

TL;DR: The Hierarchical Probabilistic U-Net is proposed, a segmentation network with a conditional variational auto-encoder (cVAE) that uses a hierarchical latent space decomposition that automatically separates independent factors across scales, an inductive bias that is deemed beneficial in structured output prediction tasks beyond segmentation.

TL;DR: In this paper, the authors unify the two stages and learn the image classifiers and a set of shared parts jointly, and introduce the notion of negative parts, intended as parts that are negatively correlated with one or more classes.

TL;DR: This paper proposes a network architecture which aggregates and embeds the face descriptors produced by deep convolutional neural networks into a compact fixed-length representation, and proposes a novel GhostVLAD layer that includes ghost clusters that do not contribute to the aggregation.

TL;DR: A method of using nonmetric visual information derived from an uncalibrated active vision system to navigate an autonomous vehicle through free-space regions detected in a cluttered environment is demonstrated.