Publications related to Hessian affine region detector

Dynamical low rank approximation for uncertainty quantification of time-dependent problems

The quantification of uncertainties can be particularly challenging for problems requiring long-time integration as the structure of the random solution might considerably change over time. In this respect, dynamical low-rank approximation (DLRA) is very a ...

EPFL2022

On Matching Pursuit and Coordinate Descent

Martin Jaggi, Sebastian Urban Stich, Sai Praneeth Reddy Karimireddy, Anant Raj

Two popular examples of first-order optimization methods over linear spaces are coordinate descent and matching pursuit algorithms, with their randomized variants. While the former targets the optimization by moving along coordinates, the latter considers ...

2018

Geometric Variational Models for Inverse Problems in Imaging

Virginia Estellers Casas

This dissertation develops geometric variational models for different inverse problems in imaging that are ill-posed, designing at the same time efficient numerical algorithms to compute their solutions. Variational methods solve inverse problems by the fo ...

EPFL2013

Learning Image Descriptors with the Boosting-Trick

Pascal Fua, Vincent Lepetit, Tomasz Piotr Trzcinski, Christos Marios Christoudias

In this paper we apply boosting to learn complex non-linear local visual feature representations, drawing inspiration from its successful application to visual object detection. The main goal of local feature descriptors is to distinctively repre- sent a s ...

2012

Alternative Search Techniques for Face Detection Using Location Estimation and Binary Features

Venkatesh Bala Subburaman

The sliding window approach is the most widely used technique to detect objects from an image. In the past few years, classifiers have been improved in many ways to increase the scanning speed. Apart from the classifier design (such as the cascade), the sc ...

EPFL2012

Learning Real-Time Perspective Patch Rectification

Pascal Fua, Vincent Lepetit

We propose two learning-based methods to patch rectification that are faster and more reliable than state-of-the-art affine region detection methods. Given a reference view of a patch, they can quickly recognize it in new views and accurately estimate the ...

Springer Verlag2011

Finding Objects of Interest in Images using Saliency and Superpixels

Radhakrishna Achanta

The ability to automatically find objects of interest in images is useful in the areas of compression, indexing and retrieval, re-targeting, and so on. There are two classes of such algorithms – those that find any object of interest with no prior knowledg ...

EPFL2011

Spatio-Chromatic Decorrelation by Shift-Invariant Filtering

Pascal Fua, Sabine Süsstrunk, Matthew Brown

In this paper we derive convolutional filters for colour image whitening and decorrelation. Whilst whitening can be achieved via eigendecomposition of the image patch covariance, this operation is neither efficient nor biologically plausible. Given the shi ...

2011

Blob current structures in TORPEX plasmas: experimental measurements and numerical simulations

Ambrogio Fasoli, Ivo Furno, Paolo Ricci, Christian Gabriel Theiler, Nicola Vianello, Davoud Iraji, Diane Virginie Marie Lançon

In the simple magnetized torus TORPEX, field-aligned blobs originate from ideal interchange waves and propagate radially outward due to del B and curvature induced drifts. Time-resolved two-dimensional measurements of the field-aligned current density J(pa ...

2011

Cascade of Descriptors to Detect and Track Objects Across Any Network of Cameras

Michel Bierlaire, Pierre Vandergheynst, Murat Kunt, Alexandre Massoud Alahi

Most of the multi-camera systems assume a well structured environment to detect and match objects across cameras. Cameras need to be fixed and calibrated. In this work, a novel system is presented to detect and match any objects in a network of uncalibrate ...

Elsevier2010

Appearance-based Keypoint Clustering

Pascal Fua, Sabine Süsstrunk, Vincent Lepetit, Francisco Estrada

We present an algorithm for clustering sets of detected interest points into groups that correspond to visually distinct structure. Through the use of a suitable colour and texture representation, our clustering method is able to identify keypoints that be ...

2009

Variational methods for texture segmentation

Nawal Houhou

In the last decades, image production has grown significantly. From digital photographs to the medical scans, including satellite images and video films, more and more data need to be processed. Consequently the number of applications based on digital imag ...

EPFL2009

Object Detection and Matching with Mobile Cameras Collaborating with Fixed Cameras

Michel Bierlaire, Murat Kunt, Alexandre Massoud Alahi

A system is presented to detect and match any objects with mobile cameras collaborating with fixed cameras observing the same scene. No training data is needed. Various object descriptors are studied based on grids of region descriptors. Region descriptors ...

2008

Prior knowledge in Kernel methods

Alexei Pozdnoukhov

Machine Learning is a modern and actively developing field of computer science, devoted to extracting and estimating dependencies from empirical data. It combines such fields as statistics, optimization theory and artificial intelligence. In practical task ...

EPFL2006