activity
20152023
most citedAutoNovel: Automatically Discovering and Learning Novel Visual Categories

151 citations · 561 across the 38 of their papers we have counts for

collaborators
Showing 2018Show all

16 papers · 1 filter

cs.CV2018

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

Jie Hu, Li Shen, Samuel Albanie +2

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from captu…

cs.CV2018

Learning to Read by Spelling: Towards Unsupervised Text Recognition

Ankush Gupta, Andrea Vedaldi, Andrew Zisserman

This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distrib…

cs.CV2018

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild

Samuel Albanie, Arsha Nagrani, Andrea Vedaldi +1

Obtaining large, human labelled speech datasets to train models for emotion recognition is a notoriously challenging task, hindered by annotation cost and label ambiguity. In this…

cs.CV2018

Semi-convolutional Operators for Instance Segmentation

David Novotny, Samuel Albanie, Diane Larlus +1

Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN. However, there is a growing interest in reducing these problems to pixel labelin…

cs.CV2018

Inductive Visual Localisation: Factorised Training for Superior Generalisation

Ankush Gupta, Andrea Vedaldi, Andrew Zisserman

End-to-end trained Recurrent Neural Networks (RNNs) have been successfully applied to numerous problems that require processing sequences, such as image captioning, machine transla…

cs.CV2018

Large scale evaluation of local image feature detectors on homography datasets

Karel Lenc, Andrea Vedaldi

We present a large scale benchmark for the evaluation of local feature detectors. Our key innovation is the introduction of a new evaluation protocol which extends and improves the…