Alert button
Picture for Andrea Vedaldi

Andrea Vedaldi

Alert button

Calibrating Self-supervised Monocular Depth Estimation

Sep 16, 2020
Robert McCraith, Lukas Neumann, Andrea Vedaldi

Figure 1 for Calibrating Self-supervised Monocular Depth Estimation
Figure 2 for Calibrating Self-supervised Monocular Depth Estimation
Figure 3 for Calibrating Self-supervised Monocular Depth Estimation
Figure 4 for Calibrating Self-supervised Monocular Depth Estimation
Viaarxiv icon

Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

Aug 28, 2020
David Novotny, Roman Shapovalov, Andrea Vedaldi

Figure 1 for Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
Figure 2 for Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
Figure 3 for Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
Figure 4 for Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
Viaarxiv icon

Automatic Recall Machines: Internal Replay, Continual Learning and the Brain

Jul 15, 2020
Xu Ji, Joao Henriques, Tinne Tuytelaars, Andrea Vedaldi

Figure 1 for Automatic Recall Machines: Internal Replay, Continual Learning and the Brain
Figure 2 for Automatic Recall Machines: Internal Replay, Continual Learning and the Brain
Figure 3 for Automatic Recall Machines: Internal Replay, Continual Learning and the Brain
Figure 4 for Automatic Recall Machines: Internal Replay, Continual Learning and the Brain
Viaarxiv icon

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

Jul 02, 2020
Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi

Figure 1 for RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Figure 2 for RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Figure 3 for RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Figure 4 for RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Viaarxiv icon

Labelling unlabelled videos from scratch with multi-modal self-supervision

Jun 24, 2020
Yuki M. Asano, Mandela Patrick, Christian Rupprecht, Andrea Vedaldi

Figure 1 for Labelling unlabelled videos from scratch with multi-modal self-supervision
Figure 2 for Labelling unlabelled videos from scratch with multi-modal self-supervision
Figure 3 for Labelling unlabelled videos from scratch with multi-modal self-supervision
Figure 4 for Labelling unlabelled videos from scratch with multi-modal self-supervision
Viaarxiv icon

LSD-C: Linearly Separable Deep Clusters

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

Figure 1 for LSD-C: Linearly Separable Deep Clusters
Figure 2 for LSD-C: Linearly Separable Deep Clusters
Figure 3 for LSD-C: Linearly Separable Deep Clusters
Figure 4 for LSD-C: Linearly Separable Deep Clusters
Viaarxiv icon

VGGSound: A Large-scale Audio-Visual Dataset

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

Figure 1 for VGGSound: A Large-scale Audio-Visual Dataset
Figure 2 for VGGSound: A Large-scale Audio-Visual Dataset
Figure 3 for VGGSound: A Large-scale Audio-Visual Dataset
Figure 4 for VGGSound: A Large-scale Audio-Visual Dataset
Viaarxiv icon

Fixing the train-test resolution discrepancy: FixEfficientNet

Apr 20, 2020
Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

Figure 1 for Fixing the train-test resolution discrepancy: FixEfficientNet
Figure 2 for Fixing the train-test resolution discrepancy: FixEfficientNet
Figure 3 for Fixing the train-test resolution discrepancy: FixEfficientNet
Viaarxiv icon

Monocular Depth Estimation with Self-supervised Instance Adaptation

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

Figure 1 for Monocular Depth Estimation with Self-supervised Instance Adaptation
Figure 2 for Monocular Depth Estimation with Self-supervised Instance Adaptation
Figure 3 for Monocular Depth Estimation with Self-supervised Instance Adaptation
Figure 4 for Monocular Depth Estimation with Self-supervised Instance Adaptation
Viaarxiv icon