Andrew Zisserman

verfied profile

∙ 2 followers
Google ∙ University of Oxford

Professor of computer vision at the University of Oxford. Since 2014, he is also a member of DeepMind.

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

We consider the problem of discovering novel object categories in an ima...
08/26/2019 ∙ by Kai Han, et al. ∙ 112 ∙ share

read it
Self-supervised learning of class embeddings from video

This work explores how to use self-supervised learning on videos to lear...
10/28/2019 ∙ by Olivia Wiles, et al. ∙ 41 ∙ share

read it
End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Annotating videos is cumbersome, expensive and not scalable. Yet, many s...
12/13/2019 ∙ by Antoine Miech, et al. ∙ 35 ∙ share

read it
Geometry-Aware Video Object Detection for Static Cameras

In this paper we propose a geometry-aware model for video object detecti...
09/06/2019 ∙ by Dan Xu, et al. ∙ 34 ∙ share

read it
Count, Crop and Recognise: Fine-Grained Recognition in the Wild

The goal of this paper is to label all the animal individuals present in...
09/19/2019 ∙ by Max Bain, et al. ∙ 34 ∙ share

read it
A Geometric Approach to Obtain a Bird's Eye View from an Image

The objective of this paper is to rectify any monocular image by computi...
05/06/2019 ∙ by Ammar Abbas, et al. ∙ 32 ∙ share

read it
The VGG Image Annotator (VIA)

Manual image annotation, such as defining and labelling regions of inter...
04/24/2019 ∙ by Abhishek Dutta, et al. ∙ 30 ∙ share

read it
Controllable Attention for Structured Layered Video Decomposition

The objective of this paper is to be able to separate a video into its n...
10/24/2019 ∙ by Jean-Baptiste Alayrac, et al. ∙ 24 ∙ share

read it
ASR is all you need: cross-modal distillation for lip reading

The goal of this work is to train strong models for visual speech recogn...
11/28/2019 ∙ by Triantafyllos Afouras, et al. ∙ 24 ∙ share

read it
Video Action Transformer Network

We introduce the Action Transformer model for recognizing and localizing...
12/06/2018 ∙ by Rohit Girdhar, et al. ∙ 20 ∙ share

read it
Synthetic Humans for Action Recognition from Unseen Viewpoints

Our goal in this work is to improve the performance of human action reco...
12/09/2019 ∙ by Gül Varol, et al. ∙ 17 ∙ share

read it
Disentangled Speech Embeddings using Cross-modal Self-supervision

The objective of this paper is to learn representations of speaker ident...
02/20/2020 ∙ by Arsha Nagrani, et al. ∙ 17 ∙ share

read it
Video Representation Learning by Dense Predictive Coding

The objective of this paper is self-supervised learning of spatio-tempor...
09/10/2019 ∙ by Tengda Han, et al. ∙ 16 ∙ share

read it
Automatically Discovering and Learning New Visual Categories with Ranking Statistics

We tackle the problem of discovering novel classes in an image collectio...
02/13/2020 ∙ by Kai Han, et al. ∙ 13 ∙ share

read it
Object Discovery with a Copy-Pasting GAN

We tackle the problem of object discovery, where objects are segmented f...
05/27/2019 ∙ by Relja Arandjelović, et al. ∙ 12 ∙ share

read it
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition

We focus on multi-modal fusion for egocentric action recognition, and pr...
08/22/2019 ∙ by Evangelos Kazakos, et al. ∙ 12 ∙ share

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

Obtaining large, human labelled speech datasets to train models for emot...
08/16/2018 ∙ by Samuel Albanie, et al. ∙ 8 ∙ share

read it
Class-Agnostic Counting

Nearly all existing counting methods are designed for a specific object ...
11/01/2018 ∙ by Erika Lu, et al. ∙ 8 ∙ share

read it
The StreetLearn Environment and Dataset

Navigation is a rich and well-grounded problem domain that drives progre...
03/04/2019 ∙ by Piotr Mirowski, et al. ∙ 8 ∙ share

read it
Exploiting temporal context for 3D human pose estimation in the wild

We present a bundle-adjustment-based algorithm for recovering accurate 3...
05/10/2019 ∙ by Anurag Arnab, et al. ∙ 8 ∙ share

read it
LAEO-Net: revisiting people Looking At Each Other in videos

Capturing the `mutual gaze' of people is essential for understanding and...
06/12/2019 ∙ by Manuel J. Marín-Jimenez, et al. ∙ 8 ∙ share

read it
Comparator Networks

The objective of this work is set-based verification, e.g. to decide if ...
07/30/2018 ∙ by Weidi Xie, et al. ∙ 6 ∙ share

read it
From Same Photo: Cheating on Visual Kinship Challenges

With the propensity for deep learning models to learn unintended signals...
09/17/2018 ∙ by Mitchell Dawson, et al. ∙ 6 ∙ share

read it
Learning to Read by Spelling: Towards Unsupervised Text Recognition

This work presents a method for visual text recognition without using an...
09/23/2018 ∙ by Ankush Gupta, et al. ∙ 6 ∙ share

read it
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities

Medical imaging only indirectly measures the molecular identity of the t...
05/30/2019 ∙ by Simon A. A. Kohl, et al. ∙ 5 ∙ share

read it
VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge

The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well...
12/05/2019 ∙ by Joon Son Chung, et al. ∙ 5 ∙ share

read it
Deep Lip Reading: a comparison of models and an online application

The goal of this paper is to develop state-of-the-art models for lip rea...
06/15/2018 ∙ by Triantafyllos Afouras, et al. ∙ 4 ∙ share

read it
X2Face: A network for controlling face generation by using images, audio, and pose codes

The objective of this paper is a neural network model that controls the ...
07/27/2018 ∙ by Olivia Wiles, et al. ∙ 4 ∙ share

read it
Self-supervised learning of a facial attribute embedding from video

We propose a self-supervised framework for learning facial attributes by...
08/21/2018 ∙ by Olivia Wiles, et al. ∙ 4 ∙ share

read it
Semi-Supervised Learning with Scarce Annotations

While semi-supervised learning (SSL) algorithms provide an efficient way...
05/21/2019 ∙ by Sylvestre-Alvise Rebuffi, et al. ∙ 3 ∙ share

read it
Use What You Have: Video Retrieval Using Representations From Collaborative Experts

The rapid growth of video on the internet has made searching for video c...
07/31/2019 ∙ by Yang Liu, et al. ∙ 3 ∙ share

read it
My lips are concealed: Audio-visual speech enhancement through obstructions

Our objective is an audio-visual model for separating a single speaker f...
07/11/2019 ∙ by Triantafyllos Afouras, et al. ∙ 3 ∙ share

read it
Multicolumn Networks for Face Recognition

The objective of this work is set-based face recognition, i.e. to decide...
07/24/2018 ∙ by Weidi Xie, et al. ∙ 2 ∙ share

read it
Deep Audio-Visual Speech Recognition

The goal of this work is to recognise phrases and sentences being spoken...
09/06/2018 ∙ by Triantafyllos Afouras, et al. ∙ 2 ∙ share

read it
The Visual Centrifuge: Model-Free Layered Video Representations

True video understanding requires making sense of non-lambertian scenes ...
12/04/2018 ∙ by Jean-Baptiste Alayrac, et al. ∙ 2 ∙ share

read it
Temporal Cycle-Consistency Learning

We introduce a self-supervised representation learning method based on t...
04/16/2019 ∙ by Debidatta Dwibedi, et al. ∙ 2 ∙ share

read it
Utterance-level Aggregation For Speaker Recognition In The Wild

The objective of this paper is speaker recognition "in the wild"-where u...
02/26/2019 ∙ by Weidi Xie, et al. ∙ 2 ∙ share

read it
Sim2real transfer learning for 3D pose estimation: motion to the rescue

Simulation is an anonymous, low-bias source of data where annotation can...
07/04/2019 ∙ by Carl Doersch, et al. ∙ 1 ∙ share

read it
A Short Note on the Kinetics-700 Human Action Dataset

We describe an extension of the DeepMind Kinetics human action dataset f...
07/15/2019 ∙ by Joao Carreira, et al. ∙ 1 ∙ share

read it
Trusting SVM for Piecewise Linear CNNs

We present a novel layerwise optimization algorithm for the learning obj...
11/07/2016 ∙ by Leonard Berrada, et al. ∙ 0 ∙ share

read it
Personalizing Human Video Pose Estimation

We propose a personalized ConvNet pose estimator that automatically adap...
11/20/2015 ∙ by James Charles, et al. ∙ 0 ∙ share

read it
SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes

The objective of this paper is 3D shape understanding from single and mu...
11/21/2017 ∙ by Olivia Wiles, et al. ∙ 0 ∙ share

read it
VGGFace2: A dataset for recognising faces across pose and age

In this paper, we introduce a new large-scale face dataset named VGGFace...
10/23/2017 ∙ by Qiong Cao, et al. ∙ 0 ∙ share

read it
Detect to Track and Track to Detect

Recent approaches for high accuracy detection and tracking of object cat...
10/11/2017 ∙ by Christoph Feichtenhofer, et al. ∙ 0 ∙ share

read it
Recurrent Human Pose Estimation

We propose a novel ConvNet model for predicting 2D human body poses in a...
05/10/2016 ∙ by Vasileios Belagiannis, et al. ∙ 0 ∙ share

read it
Multi-task Self-Supervised Visual Learning

We investigate methods for combining multiple self-supervised tasks--i.e...
08/25/2017 ∙ by Carl Doersch, et al. ∙ 0 ∙ share

read it
Self-Supervised Learning for Spinal MRIs

A significant proportion of patients scanned in a clinical setting have ...
08/01/2017 ∙ by Amir Jamaludin, et al. ∙ 0 ∙ share

read it
Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video

We present an automatic method to describe clinically useful information...
07/03/2017 ∙ by Weilin Huang, et al. ∙ 0 ∙ share

read it
Look, Listen and Learn

We consider the question: what can be learnt by looking at and listening...
05/23/2017 ∙ by Relja Arandjelović, et al. ∙ 0 ∙ share

read it
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

The paucity of videos in current action classification datasets (UCF-101...
05/22/2017 ∙ by Joao Carreira, et al. ∙ 0 ∙ share

read it

Andrew Zisserman

Featured Co-authors