List of works - Andrea Vedaldi

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

scientific article published in November 2020

A Compact and Discriminative Face Track Descriptor

A Complexity-Distortion Approach to Joint Pattern Alignment ⬇️

scientific article published in January 2007

A coarse-to-fine approach for fast deformable object detection

scholarly article by Marco Pedersoli et al published May 2015 in Pattern Recognition

A coarse-to-fine approach for fast deformable object detection

Accurate brain age prediction with lightweight deep neural networks

scientific article published on 19 October 2020

Action Recognition with Dynamic Image Networks

scientific article published on 02 November 2017

Blocks That Shout: Distinctive Parts for Scene Classification

Boosting Invariance and Efficiency in Supervised Learning

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

scientific article published in November 2020

Capturing the Geometry of Object Categories from Video Supervision

scientific article published on 19 September 2018

Continuous Surface Embeddings ⬇️

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels ⬇️

Deep Features for Text Spotting

Deep Filter Banks for Texture Recognition, Description, and Segmentation

scientific article published on 09 January 2016

Deep Fisher Networks for Large-Scale Image Classification ⬇️

Describing Textures in the Wild

scholarly article published June 2014

Descriptor Learning Using Convex Optimisation

Efficient additive kernels via explicit feature maps

scientific article

Efficient additive kernels via explicit feature maps

Explanations for Attributing Deep Neural Network Predictions

scientific article published in 2019

Fisher Vector Faces in the Wild

Fixing the train-test resolution discrepancy ⬇️

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks ⬇️

scholarly article by Jie Hu et al published 2018 in Advances in Neural Information Processing Systems 31

Generalized RBF feature maps for Efficient Detection

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

scientific article published on 10 May 2019

Integrated perception with recurrent multi-task neural networks ⬇️

scientific article published in January 2016

Interpretable Explanations of Black Boxes by Meaningful Perturbation

scientific article published in October 2017

Joint data alignment up to (lossy) transformations

Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition

article by Andrea Vedaldi et al published 2010 in Studies in Computational Intelligence

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

scientific article published in November 2020

Learning Local Feature Descriptors Using Convex Optimisation

scientific article published on August 2014

Learning equivariant structured output SVM regressors

Learning feed-forward one-shot learners ⬇️

scientific article published in January 2016

Learning multiple visual domains with residual adapters ⬇️

scientific article published in January 2017

Modelling and unsupervised learning of symmetric deformable object categories ⬇️

Moving Forward in Structure From Motion

MultiGrain: a unified image embedding for classes and instances ⬇️

Multiple kernels for object detection

article

Net2Vec: Quantifying and Explaining How Concepts are Encoded by Filters in Deep Neural Networks

scientific article published in June 2018

Objects in Context

On Compositions of Transformations in Contrastive Self-Supervised Learning

scholarly article published in March 2020

On-the-fly specific person retrieval

scholarly article published May 2012

Optimising a Simple Fully Convolutional Network for Accurate Brain Age Prediction in the PAC 2019 Challenge

scientific article published on 10 May 2021

Pylon Model for Semantic Segmentation ⬇️

scientific article published in January 2011

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning ⬇️

scientific article published in November 2020

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

scientific article published in November 2020

Relaxed matching kernels for robust image comparison

Self-similar Sketch

Simultaneous Object Detection and Ranking with Weak Supervision ⬇️

Structured output regression for detection with partial truncation ⬇️

scientific article published in January 2009

Supervising the New with the Old: Learning SFM from SFM

Support-set bottlenecks for video-text representation learning

scholarly article published in October 2020

The Sixth Visual Object Tracking VOT2018 Challenge Results

scientific article published in 2019

The truth about cats and dogs

Understanding Image Representations by Measuring Their Equivariance and Equivalence.

scientific article

Understanding Objects in Detail with Fine-Grained Attributes

Understanding deep image representations by inverting them

Unsupervised Learning of Object Landmarks through Conditional Image Generation ⬇️

Unsupervised learning of object frames by dense equivariant image labelling ⬇️

scientific article published in January 2017

List of works by Andrea Vedaldi

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

A Compact and Discriminative Face Track Descriptor

A Complexity-Distortion Approach to Joint Pattern Alignment ⬇️

A coarse-to-fine approach for fast deformable object detection

A coarse-to-fine approach for fast deformable object detection

Accurate brain age prediction with lightweight deep neural networks

Action Recognition with Dynamic Image Networks

Blocks That Shout: Distinctive Parts for Scene Classification

Boosting Invariance and Efficiency in Supervised Learning

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

Capturing the Geometry of Object Categories from Video Supervision

Continuous Surface Embeddings ⬇️

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels ⬇️

Deep Features for Text Spotting

Deep Filter Banks for Texture Recognition, Description, and Segmentation

Deep Fisher Networks for Large-Scale Image Classification ⬇️

Describing Textures in the Wild

Descriptor Learning Using Convex Optimisation

Efficient additive kernels via explicit feature maps

Efficient additive kernels via explicit feature maps

Explanations for Attributing Deep Neural Network Predictions

Fisher Vector Faces in the Wild

Fixing the train-test resolution discrepancy ⬇️

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks ⬇️

Generalized RBF feature maps for Efficient Detection

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

Integrated perception with recurrent multi-task neural networks ⬇️

Interpretable Explanations of Black Boxes by Meaningful Perturbation

Joint data alignment up to (lossy) transformations

Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition

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

Learning Local Feature Descriptors Using Convex Optimisation

Learning equivariant structured output SVM regressors

Learning feed-forward one-shot learners ⬇️

Learning multiple visual domains with residual adapters ⬇️

Modelling and unsupervised learning of symmetric deformable object categories ⬇️

Moving Forward in Structure From Motion

MultiGrain: a unified image embedding for classes and instances ⬇️

Multiple kernels for object detection

Net2Vec: Quantifying and Explaining How Concepts are Encoded by Filters in Deep Neural Networks

Objects in Context

On Compositions of Transformations in Contrastive Self-Supervised Learning

On-the-fly specific person retrieval

Optimising a Simple Fully Convolutional Network for Accurate Brain Age Prediction in the PAC 2019 Challenge

Pylon Model for Semantic Segmentation ⬇️

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning ⬇️

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

Relaxed matching kernels for robust image comparison

Self-similar Sketch

Simultaneous Object Detection and Ranking with Weak Supervision ⬇️

Structured output regression for detection with partial truncation ⬇️

Supervising the New with the Old: Learning SFM from SFM

Support-set bottlenecks for video-text representation learning

The Sixth Visual Object Tracking VOT2018 Challenge Results

The truth about cats and dogs

Understanding Image Representations by Measuring Their Equivariance and Equivalence.

Understanding Objects in Detail with Fine-Grained Attributes

Understanding deep image representations by inverting them

Unsupervised Learning of Object Landmarks through Conditional Image Generation ⬇️

Unsupervised learning of object frames by dense equivariant image labelling ⬇️

VLFeat: An open and portable library of computer vision algorithms

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions