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
Book ChapterDOI
The 2005 PASCAL visual object classes challenge
Mark Everingham,Andrew Zisserman,Christopher Williams,Luc Van Gool,Moray Allan,Christopher M. Bishop,Olivier Chapelle,Navneet Dalal,Thomas Deselaers,Gyuri Dorkó,Stefan Duffner,J Eichhorn,Jason Farquhar,Mario Fritz,Christophe Garcia,Tom Griffiths,Frédéric Jurie,Daniel Keysers,Markus Koskela,Jorma Laaksonen,Diane Larlus,Bastian Leibe,Hongying Meng,Hermann Ney,Bernt Schiele,Cordelia Schmid,Edgar Seemann,John Shawe-Taylor,Amos Storkey,Sandor Szedmak,Bill Triggs,Ilkay Ulusoy,Ville Viitaniemi,Jianguo Zhang +33 more
TL;DR: The PASCAL Visual Object Classes Challenge (PASCALVOC) as mentioned in this paper was held from February to March 2005 to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects).
Book ChapterDOI
A boundary-fragment-model for object detection
TL;DR: The BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance, and to achieve this with less supervision (such as the number of training images).
Proceedings ArticleDOI
Learning and Using the Arrow of Time
TL;DR: A ConvNet suitable for extended temporal footprints and for class activation visualization, and the effect of artificial cues, such as cinematographic conventions, on learning is studied, which achieves state-of-the-art performance on large-scale real-world video datasets.
Proceedings ArticleDOI
Video Representation Learning by Dense Predictive Coding
TL;DR: With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101 and HMDB51, outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.
Journal ArticleDOI
Harvesting Image Databases from the Web
TL;DR: A multi-modal approach employing both text, meta data and visual features is used to gather many, high-quality images from the Web to automatically generate a large number of images for a specified object class.