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
Journal ArticleDOI
From Images to 3D Shape Attributes
TL;DR: In this paper, the 3D shape attributes and embedding can be obtained from a single image by training a Convolutional Neural Network (CNN) for this task, which can be used to match previously unseen sculptures largely independent of viewpoint.
Assessing the significance of performance differences on the PASCAL VOC challenges via bootstrapping
Mark Everingham,S. M. Ali Eslami,Luc Van Gool,Christopher Williams,John Winn,Andrew Zisserman +5 more
TL;DR: The use of bootstrap sampling to address the question of whether the highest-scoring entry in a particular competition is significantly better than some of the others in terms of a specified metric.
Proceedings Article
With a Little Help From My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
TL;DR: Nearest-Neighbor Contrastive Learning of visual representations (NNCLR) as mentioned in this paper samples the nearest neighbors from the dataset in the latent space, and treats them as positives, which provides more semantic variations than pre-defined transformations.
Posted Content
Count, Crop and Recognise: Fine-Grained Recognition in the Wild
TL;DR: A 'Count, Crop and Recognise' (CCR) multi-stage recognition process for frame level labelling for chimpanzee recognition in the wild is introduced and a high-granularity visualisation technique is applied to further understand the learned CNN features for the recognition of chimpanzee individuals.
Proceedings ArticleDOI
Discovery of Rare Phenotypes in Cellular Images Using Weakly Supervised Deep Learning
TL;DR: This work proposes a deep learning approach that can detect the presence or absence of rare cellular phenotypes from weak annotations and demonstrates that the Weakly Supervised Convolutional Neural Network (WSCNN) can reliably estimate the location of the identified rare events.