Steerable PCA for Rotation-Invariant Image Recognition

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We consider the problem of comparing several samples of stochastic processes with respect to their second-order structure, and describing the main modes of variation in this second order structure, if present. These tasks can be seen as an Analysis of Vari ...

We study the problem of learning unknown parameters in stochastic interacting particle systems with polynomial drift, interaction, and diffusion functions from the path of one single particle in the system. Our estimator is obtained by solving a linear sys ...

Colloid particle size plays an important role in contaminant adsorption and clogging in the hyporheic zone, but it remains unclear how the particle size changes during the transport of colloids. This study investigated the variation of the particle size of ...

Effective Prognostics and Health Management (PHM) relies on accurate prediction of the Remaining Useful Life (RUL). Data-driven RUL prediction techniques rely heavily on the representativeness of the available time-to-failure trajectories. Therefore, these ...

Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private data distributed among multiple data providers while ensuring data confi ...

We address the effect of elastic inhomogeneity on elastic modulus and hardness determinations made by depth-sensing indentations performed on individual particles embedded within a matrix of different elastic modulus. Finite element simulations and nanoind ...

This dataset contains particle number concentrations and a pollution flag in 1 min time resolution. It is derived by the pollution detection algorithm (PDA, doi:10.5281/zenodo.5761101) based on the corrected particle number concentration data of the CPC377 ...

The invention concerns a single-particle inductively-coupled plasma (ICP) mass spectrometry particle sizing and counting method comprising providing or receiving an intensity-versus-counts histogram of particles detected using an ICP mass spectrometer, the ...

Device, system and method for sorting particles comprised into a fluid are disclosed that improve the current settings of deterministic lateral displacement (DLD)-based microfluidic devices, so to sort and detect small particles such as extracellular vesic ...

Water significantly influences the mechanical behaviour of all granular materials but none as much as hygroscopic amorphous particles. With sufficiently high water content, particles can swell, agglomerate and their mechanical properties can be reduced, ha ...

We derive a dynamical field theory for self-propelled particles subjected to generic torques and forces by explicitly coarse-graining their microscopic dynamics, described by a many-body Fokker-Planck equation. The model includes both intrinsic torques ind ...

Single-particle tracking and optical tweezers are powerful techniques for studying diverse processes at the microscopic scale. The stochastic behavior of a microscopic particle contains information about its interaction with surrounding molecules, and an o ...

ESP particle collector (1) for collecting particles in a particle containing gas stream, comprising an inlet section (4), a collector section (6), and an electrode arrangement (8), the inlet section comprising a flow tube (10) defining a gas flow channel ( ...

Encapsulation techniques open up new possibilities to control the kinetics and location of the release of active ingredients. Despite the progresses achieved to obtain a better control over the dimensions and composition of the capsules, the encapsulation ...

The Future Circular Collider (FCC-hh) is a proposed successor of the Large Hadron Collider (LHC). FCC-hh would push both the energy and intensity frontiers of searches for new physics particles. In particular, due to higher energy and luminosity than at th ...

This dataset contains a pollution flag in 1 min time resolution. It is derived by the pollution detection algorithm (PDA) based on the corrected particle number concentration data (DOI upcoming) measured during the year long MOSAiC expedition from October ...

Starting from a strong Lattice-Free Maximum Mutual Information (LF-MMI) baseline system, we explore different autoencoder configurations to enhance Mel-Frequency Cepstral Coefficients (MFCC) features. Autoencoders are expected to generate new MFCC features ...

Invariance under time translation (or stationarity) is probably one of the most important assumptions made when investigating electromagnetic phenomena. Breaking this assumption is expected to open up novel possibilities and result in exceeding conventiona ...

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 ...

The rapid development of autonomous driving and mobile mapping calls for off-the-shelf LiDAR SLAM solutions that are adaptive to LiDARs of different specifications on various complex scenarios. To this end, we propose MULLS, an efficient, low-drift, and ve ...

Steerable PCA for Rotation-Invariant Image Recognition

Chat with Graph Search

Transportation-based functional ANOVA and PCA for covariance operators

A Method of Moments Estimator for Interacting Particle Systems and their Mean Field Limit

Effects of Hyporheic Exchange and Settlement on the Particle Size Distribution of Colloids

Domain adaptation via alignment of operation profile for Remaining Useful Lifetime prediction

Scalable and Privacy-Preserving Federated Principal Component Analysis

Nanoindentation of embedded particles

Pollution mask for the continuous corrected particle number concentration data in 1 min time resolution measured in the Swiss aerosol container using a whole air inlet during MOSAiC 2019/2020

Single-particle inductively-coupled plasma mass spectrometry particle sizing and counting method, system, computer program and computer-readable data carrier

Particle-sorting fluidic device and methods for using thereof

The effect of high relative humidity on a network of water-sensitive particles (couscous) as revealed by in situ X-ray tomography

Microscopic field theory for structure formation in systems of self-propelled particles with generic torques

Probing Surfactant Bilayer Interactions by Tracking Optically Trapped Single Nanoparticles

Electrostatic particle collector

Drops: Controlled crystallization of organic crystals and their use as matrix materials for encapsulation of volatiles

Exploring the potential of FCC-hh to search for particles from B mesons

Pollution mask for the continuous corrected particle number concentration data in 1 min resolution, measured in the Swiss aerosol container during MOSAiC 2019/2020

From Undercomplete to Sparse Overcomplete Autoencoders to Improve LF-MMI Speech Recognition

Dipole polarizability of time-varying particles

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

MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square