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
Posted Content
From Images to 3D Shape Attributes
TL;DR: This paper investigates properties of 3D shape that can be determined from a single image by training a Convolutional Neural Network for this task and shows which regions of the imaged sculpture are used by the CNN to infer3D shape attributes.
Proceedings ArticleDOI
Automatic retrieval of visual continuity errors in movies
TL;DR: A scheme for automatically detecting continuity errors in feature length movies and producing a ranked list of the most likely inconsistencies, working from a commercial DVD release is developed.
ExTOL: Automatic recognition of British Sign Language using the BSL Corpus
TL;DR: The project “ExTOL: End to End Translation of British Sign language” is described, which has one aim of building the world's first British Sign Language to English translation system and the first practically functional machine translation system for any sign language.
Book ChapterDOI
Predicting Scoliosis in DXA Scans Using Intermediate Representations.
TL;DR: A method to automatically predict scoliosis in Dual-energy X-ray Absorptiometry (DXA) scans is described and it is shown that intermediate representations, which in this case are segments of body parts, help improve performance.
Proceedings ArticleDOI
Automated visual identification of characters in situation comedies
Mark Everingham,Andrew Zisserman +1 more
TL;DR: A 3-D ellipsoid approximation of the person's head is used to train a set of generative parts-based 'constellation' models which propose candidate detections in an image and results are demonstrated of detecting three characters in a TV situation comedy.