A
Andrew Zisserman
Researcher at University of Oxford
Publications - 808
Citations - 312028
Andrew Zisserman is an academic researcher from University of Oxford. The author has contributed to research in topics: Convolutional neural network & Real image. The author has an hindex of 167, co-authored 808 publications receiving 261717 citations. Previous affiliations of Andrew Zisserman include University of Edinburgh & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Efficient model library access by projectively invariant indexing functions
TL;DR: Progress in building a model-based vision system for plane objects that uses algebraic projective invariants and the recognition system is described, giving examples of the invariant techniques working on real images.
Posted Content
ASR is all you need: cross-modal distillation for lip reading
TL;DR: It is shown that ground truth transcriptions are not necessary to train a lip reading system and how arbitrary amounts of unlabelled video data can be leveraged to improve performance.
Book ChapterDOI
The Art of Detection
TL;DR: This work develops a system that learns a region-level classifier on-the-fly for an object category of a user’s choosing, which is then applied to over 60 million object regions across 210,000 paintings to retrieve localised instances of that category.
Proceedings Article
Mutual illumination
David Forsyth,Andrew Zisserman +1 more
TL;DR: The data imply that shape from shading based on the image irradiance equation make real errors on images of concave objects, and that edge detectors that respond to only step edges perform badly on polyhedral scenes and waste information.