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
Efficient, Blind, Spatially-Variant Deblurring for Shaken Images
TL;DR: This chapter describes a compact global parameterization of camera shake blur, based on the 3D rotation of the camera during the exposure, and introduces an efficient approximation to the global model, which significantly reduces the computational cost of modeling the spatially-variant blur.
Discussion for direct versus features session
Harpreet Sawhney,Andrew Zisserman,Samuel Peleg,Richard Szeliski,Michal Irani,Philip H. S. Torr,Joss Knight,Jitendra Malik,Padmanabhan Anandan +8 more
Posted Content
BBC-Oxford British Sign Language Dataset.
Samuel Albanie,Gül Varol,Liliane Momeni,Hannah Bull,Triantafyllos Afouras,Himel Chowdhury,Neil Fox,Bencie Woll,Rob Cooper,Andrew McParland,Andrew Zisserman +10 more
TL;DR: The BBC-Oxford British Sign Language (BOBSL) dataset as discussed by the authors is a large-scale video collection of British sign language (BSL), which is an extended and publicly released dataset based on the BSL-1K dataset.
Posted Content
Visual keyword spotting with attention
TL;DR: In this article, a Transpotter-based model is proposed for visual keyword spotting in silent video sequences. But the model is limited to the task of spotting spoken keywords in silent videos, and it requires full cross-modal attention between visual and phonetic streams.
Journal ArticleDOI
Bounding an archiving: assessing the relative completeness of the Jacques Toussele archive using pattern-matching and face-recognition
TL;DR: In this paper, a combination of pattern-matching and face recognition was used to find the complete archival fonds, and the results showed that the pattern matching was more accurate than face recognition.