Andrew Zisserman

TL;DR: This work proposes a distance function to match signing sequences which includes the trajectory of both hands, the hand shape and orientation, and properly models the case of hands touching and shows that by optimizing a scoring function based on multiple instance learning, it is able to extract the sign of interest from hours of signing footage, despite the very weak and noisy supervision.

TL;DR: A novel human-centric approach to detect and localize human actions in challenging video data, such as Hollywood movies, by first obtaining generic spatio-temporal human tracks and then detecting specific actions within these using a sliding window classifier.

TL;DR: This work targets the regime where individual object detectors do not work reliably due to crowding, or overlap, or size of the instances, and takes the approach of estimating an object density.

TL;DR: This work proposes a novel architecture for multi-modal temporal-binding, i.e. the combination of modalities within a range of temporal offsets, and demonstrates the importance of audio in egocentric vision, on per-class basis, for identifying actions as well as interacting objects.

TL;DR: Multi-view relationships are developed for lines, conics and non-algebraic curves using the homography induced by this plane for transfer from one image to another in a projective reconstruction of imaged curves.