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
Visual Grounding in Video for Unsupervised Word Translation
Gunnar A. Sigurdsson,Jean-Baptiste Alayrac,Aida Nematzadeh,Lucas Smaira,Mateusz Malinowski,Joao Carreira,Phil Blunsom,Andrew Zisserman +7 more
TL;DR: This article used visual grounding to improve unsupervised word mapping between languages by learning embeddings from unpaired instructional videos narrated in the native language, and applied these methods to translate words from English to French, Korean, and Japanese.
Proceedings ArticleDOI
What have We Learned from Deep Representations for Action Recognition
TL;DR: It is shown that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions in video, and cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance andmotion features.
Journal ArticleDOI
Deep Insights into Convolutional Networks for Video Recognition
TL;DR: This paper visualizes the internal representation of models that have been trained to recognize actions in video by visualizing multiple two-stream architectures to show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions.
Book ChapterDOI
Automatic Camera Tracking
TL;DR: This work states that the goal of automatic recovery of camera motion and scene structure from video sequences has been a staple of computer vision research for over a decade and now represents one of the success stories ofComputer vision.
Journal ArticleDOI
Minimal projective reconstruction for combinations of points and lines in three views
TL;DR: This paper investigates three novel minimal combinations of points and lines over three views, and gives complete solutions and reconstruction methods for two of these cases: "four points and three lines in three views", and "two points and six lines inThree views".