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
Learning to Read by Spelling: Towards Unsupervised Text Recognition
TL;DR: This work forms the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora, which enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets.
Journal ArticleDOI
Automatic 3D model building from video sequences
Luc Van Gool,Andrew Zisserman +1 more
TL;DR: Progress on automating the construction of 3D geometric models from video sequences is described, designed to ease model acquisition for virtual reality and telepresence applications, however the approach also has application in model based image coding.
Proceedings ArticleDOI
Visual navigation around curved obstacles
TL;DR: An approach to path-planning around smooth obstacles that exploits visually derived geometry is proposed, where a moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path by seeking geodesics which can be extrapolated smoothly around the obstacle and towards the goal.
Journal Article
A sparse object category model for efficient learning and complete recognition
TL;DR: A parts and structure model for object category recognition that can be learnt efficiently and in a weakly-supervised manner, bypassing the need for feature detectors, to give the globally optimal match within a query image.