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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Andrea Vedaldi

Generalized Category Discovery


Jan 07, 2022
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

* 13 pages, 6 figures 

  Access Paper or Ask Questions

BANMo: Building Animatable 3D Neural Models from Many Casual Videos


Dec 24, 2021
Gengshan Yang, Minh Vo, Natalia Neverova, Deva Ramanan, Andrea Vedaldi, Hanbyul Joo

* Modified Sec. 3.2 deformation model and Sec. 3.4 active sampling 

  Access Paper or Ask Questions

Audio-Visual Synchronisation in the wild


Dec 08, 2021
Honglie Chen, Weidi Xie, Triantafyllos Afouras, Arsha Nagrani, Andrea Vedaldi, Andrew Zisserman


  Access Paper or Ask Questions

Unsupervised Part Discovery from Contrastive Reconstruction


Nov 11, 2021
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi

* To appear in NeurIPS 2021. Project page: https://www.robots.ox.ac.uk/~vgg/research/unsup-parts/ 

  Access Paper or Ask Questions

The Curious Layperson: Fine-Grained Image Recognition without Expert Labels


Nov 05, 2021
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi

* To appear in BMVC 2021 (Oral). Project page: https://www.robots.ox.ac.uk/~vgg/research/clever/ 

  Access Paper or Ask Questions

NeuralDiff: Segmenting 3D objects that move in egocentric videos


Oct 19, 2021
Vadim Tschernezki, Diane Larlus, Andrea Vedaldi

* 3DV2021. Project page: https://www.robots.ox.ac.uk/~vadim/neuraldiff/ 

  Access Paper or Ask Questions

Open-Set Recognition: A Good Closed-Set Classifier is All You Need


Oct 12, 2021
Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman

* 23 pages, 8 figures 

  Access Paper or Ask Questions

Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views


Oct 09, 2021
Robert McCraith, Eldar Insafutdinov, Lukas Neumann, Andrea Vedaldi

* ICRA 2022 submission 

  Access Paper or Ask Questions

PASS: An ImageNet replacement for self-supervised pretraining without humans


Sep 27, 2021
Yuki M. Asano, Christian Rupprecht, Andrew Zisserman, Andrea Vedaldi

* Accepted to NeurIPS Track on Datasets and Benchmarks 2021. Webpage: https://www.robots.ox.ac.uk/~vgg/research/pass/ 

  Access Paper or Ask Questions

Real Time Monocular Vehicle Velocity Estimation using Synthetic Data


Sep 16, 2021
Robert McCraith, Lukas Neumann, Andrea Vedaldi

* IEEE Intelligent Vehicles 2021 best paper finalist 

  Access Paper or Ask Questions

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension


Aug 31, 2021
Roman Shapovalov, David Novotny, Benjamin Graham, Patrick Labatut, Andrea Vedaldi

* Accepted for ICCV 2021 

  Access Paper or Ask Questions

Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields


Aug 19, 2021
Matan Atzmon, David Novotny, Andrea Vedaldi, Yaron Lipman


  Access Paper or Ask Questions

DOVE: Learning Deformable 3D Objects by Watching Videos


Jul 22, 2021
Shangzhe Wu, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi

* Project Page: https://dove3d.github.io/ 

  Access Paper or Ask Questions

AutoNovel: Automatically Discovering and Learning Novel Visual Categories


Jun 29, 2021
Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

* TPAMI 2021, code: http://www.robots.ox.ac.uk/~vgg/research/auto_novel/. arXiv admin note: substantial text overlap with arXiv:2002.05714 

  Access Paper or Ask Questions

Discovering Relationships between Object Categories via Universal Canonical Maps


Jun 17, 2021
Natalia Neverova, Artsiom Sanakoyeu, Patrick Labatut, David Novotny, Andrea Vedaldi

* Accepted at CVPR 2021; Project page: https://gdude.de/discovering-3d-obj-rel 

  Access Paper or Ask Questions

NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go


Jun 17, 2021
Marvin Eisenberger, David Novotny, Gael Kerchenbaum, Patrick Labatut, Natalia Neverova, Daniel Cremers, Andrea Vedaldi

* Published at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021 

  Access Paper or Ask Questions

Predicting Unreliable Predictions by Shattering a Neural Network


Jun 15, 2021
Xu Ji, Razvan Pascanu, Devon Hjelm, Andrea Vedaldi, Balaji Lakshminarayanan, Yoshua Bengio


  Access Paper or Ask Questions

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers


Jun 09, 2021
Mandela Patrick, Dylan Campbell, Yuki M. Asano, Ishan Misra Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, Jo\ão F. Henriques

* Project page: https://facebookresearch.github.io/Motionformer 

  Access Paper or Ask Questions

Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes


Jun 01, 2021
Dan Xu, Andrea Vedaldi, Joao F. Henriques


  Access Paper or Ask Questions

Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models


May 17, 2021
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi

* Project page and GitHub link: https://lukemelas.github.io/unsupervised-image-segmentation & https://github.com/lukemelas/unsupervised-image-segmentation 

  Access Paper or Ask Questions

Self-supervised object detection from audio-visual correspondence


Apr 13, 2021
Triantafyllos Afouras, Yuki M. Asano, Francois Fagan, Andrea Vedaldi, Florian Metze

* Under review 

  Access Paper or Ask Questions

Localizing Visual Sounds the Hard Way


Apr 06, 2021
Honglie Chen, Weidi Xie, Triantafyllos Afouras, Arsha Nagrani, Andrea Vedaldi, Andrew Zisserman

* CVPR2021 

  Access Paper or Ask Questions

Unsupervised Learning of 3D Object Categories from Videos in the Wild


Mar 30, 2021
Philipp Henzler, Jeremy Reizenstein, Patrick Labatut, Roman Shapovalov, Tobias Ritschel, Andrea Vedaldi, David Novotny


  Access Paper or Ask Questions

Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning


Mar 18, 2021
Mandela Patrick, Yuki M. Asano, Bernie Huang, Ishan Misra, Florian Metze, Joao Henriques, Andrea Vedaldi


  Access Paper or Ask Questions

Continuous Surface Embeddings


Nov 24, 2020
Natalia Neverova, David Novotny, Vasil Khalidov, Marc Szafraniec, Patrick Labatut, Andrea Vedaldi

* NeurIPS, 2020 

  Access Paper or Ask Questions

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data


Nov 02, 2020
Benjamin Biggs, Sébastien Ehrhadt, Hanbyul Joo, Benjamin Graham, Andrea Vedaldi, David Novotny

* NeurIPS 2020 Spotlight; 14 pages including supplementary 

  Access Paper or Ask Questions

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning


Oct 27, 2020
Iro Laina, Ruth C. Fong, Andrea Vedaldi

* NeurIPS 2020 

  Access Paper or Ask Questions

Support-set bottlenecks for video-text representation learning


Oct 06, 2020
Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze, Alexander Hauptmann, João Henriques, Andrea Vedaldi


  Access Paper or Ask Questions