Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

Self-Supervised MultiModal Versatile Networks

Jun 29, 2020
Jean-Baptiste Alayrac, Adri√† Recasens, Rosalia Schneider, Relja Arandjelovińá, Jason Ramapuram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, Andrew Zisserman

  Access Model/Code and Paper
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

Jun 27, 2020
Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

* Accepted at CVPR 2020. Project webpage: 

  Access Model/Code and Paper
LSD-C: Linearly Separable Deep Clusters

Jun 17, 2020
Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Kai Han, Andrea Vedaldi, Andrew Zisserman

* Code available at 

  Access Model/Code and Paper
The AVA-Kinetics Localized Human Actions Video Dataset

May 20, 2020
Ang Li, Meghana Thotakuri, David A. Ross, Jo√£o Carreira, Alexander Vostrikov, Andrew Zisserman

* 8 pages, 8 figures 

  Access Model/Code and Paper
Condensed Movies: Story Based Retrieval with Contextual Embeddings

May 08, 2020
Max Bain, Arsha Nagrani, Andrew Brown, Andrew Zisserman

  Access Model/Code and Paper
VGGSound: A Large-scale Audio-Visual Dataset

Apr 29, 2020
Honglie Chen, Weidi Xie, Andrea Vedaldi, Andrew Zisserman

* ICASSP2020 

  Access Model/Code and Paper
Monocular Depth Estimation with Self-supervised Instance Adaptation

Apr 13, 2020
Robert McCraith, Lukas Neumann, Andrew Zisserman, Andrea Vedaldi

* IROS submission, 7 pages 

  Access Model/Code and Paper
Speech2Action: Cross-modal Supervision for Action Recognition

Mar 30, 2020
Arsha Nagrani, Chen Sun, David Ross, Rahul Sukthankar, Cordelia Schmid, Andrew Zisserman

* Accepted to CVPR 2020 

  Access Model/Code and Paper
Visual Grounding in Video for Unsupervised Word Translation

Mar 26, 2020
Gunnar A. Sigurdsson, Jean-Baptiste Alayrac, Aida Nematzadeh, Lucas Smaira, Mateusz Malinowski, Jo√£o Carreira, Phil Blunsom, Andrew Zisserman

* CVPR 2020 
* CVPR 2020 

  Access Model/Code and Paper
Compact Deep Aggregation for Set Retrieval

Mar 26, 2020
Yujie Zhong, Relja Arandjelovińá, Andrew Zisserman

* 20 pages 

  Access Model/Code and Paper
Disentangled Speech Embeddings using Cross-modal Self-supervision

Feb 20, 2020
Arsha Nagrani, Joon Son Chung, Samuel Albanie, Andrew Zisserman

* To appear in ICASSP 2020. The first three authors contributed equally to this work 

  Access Model/Code and Paper
Automatically Discovering and Learning New Visual Categories with Ranking Statistics

Feb 13, 2020
Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

* ICLR 2020, code: 

  Access Model/Code and Paper
End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Jan 17, 2020
Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev, Josef Sivic, Andrew Zisserman

  Access Model/Code and Paper
Synthetic Humans for Action Recognition from Unseen Viewpoints

Dec 09, 2019
G√ľl Varol, Ivan Laptev, Cordelia Schmid, Andrew Zisserman

  Access Model/Code and Paper
VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge

Dec 05, 2019
Joon Son Chung, Arsha Nagrani, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, Andrew Zisserman

* ISCA Archive 

  Access Model/Code and Paper
ASR is all you need: cross-modal distillation for lip reading

Nov 28, 2019
Triantafyllos Afouras, Joon Son Chung, Andrew Zisserman

  Access Model/Code and Paper
Self-supervised learning of class embeddings from video

Oct 28, 2019
Olivia Wiles, A. Sophia Koepke, Andrew Zisserman

* 4th International Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision 2019 

  Access Model/Code and Paper
Controllable Attention for Structured Layered Video Decomposition

Oct 24, 2019
Jean-Baptiste Alayrac, Jo√£o Carreira, Relja Arandjelovińá, Andrew Zisserman

* In ICCV 2019 

  Access Model/Code and Paper
Count, Crop and Recognise: Fine-Grained Recognition in the Wild

Oct 09, 2019
Max Bain, Arsha Nagrani, Daniel Schofield, Andrew Zisserman

  Access Model/Code and Paper
Video Representation Learning by Dense Predictive Coding

Sep 27, 2019
Tengda Han, Weidi Xie, Andrew Zisserman

  Access Model/Code and Paper
Geometry-Aware Video Object Detection for Static Cameras

Sep 06, 2019
Dan Xu, Weidi Xie, Andrew Zisserman

* Accepted at BMVC 2019 as ORAL 

  Access Model/Code and Paper
Learning to Discover Novel Visual Categories via Deep Transfer Clustering

Aug 26, 2019
Kai Han, Andrea Vedaldi, Andrew Zisserman

* ICCV 2019 

  Access Model/Code and Paper
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition

Aug 22, 2019
Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen

* Accepted for presentation at ICCV 2019 

  Access Model/Code and Paper
AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations

Aug 14, 2019
Honglie Chen, Weidi Xie, Andrea Vedaldi, Andrew Zisserman

* BMVC 2019 (Spotlight) 

  Access Model/Code and Paper
Use What You Have: Video Retrieval Using Representations From Collaborative Experts

Jul 31, 2019
Yang Liu, Samuel Albanie, Arsha Nagrani, Andrew Zisserman

* BMVC 2019 

  Access Model/Code and Paper