Publications associées à Height And Weight Estimation From Unconstrained Images

Publications associées (28)

Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting

Alexandre Massoud Alahi, Kaouther Messaoud Ben Amor

Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions. It is often due to limitations like complex architectures customized for a specific dataset and inefficient multimoda ...

Institute of Electrical Engineering2025

Capturing behavioral and neural variability in multi-area spiking neuronal network models

Christos Sourmpis

How does the brain generate behavioral responses from sensory stimuli? This sensor-to-motor transformation is a fundamental question in systems neuroscience. While recent experiments have highlighted the complexity of neural representations across the cere ...

EPFL2025

SIMBa: System Identification Methods Leveraging Backpropagation

Colin Neil Jones, Loris Di Natale, Giancarlo Ferrari Trecate, Muhammad Zakwan

This manuscript details and extends the system identification methods leveraging the backpropagation (SIMBa) toolbox presented in previous work, which uses well-established machine learning tools for discrete-time linear multistep-ahead state-space system ...

2024

Reliable data-driven decision-making through optimal transport

Bahar Taskesen

Decision-making permeates every aspect of human and societal development, from individuals' daily choices to the complex decisions made by communities and institutions. Central to effective decision-making is the discipline of optimization, which seeks th ...

EPFL2024

Drone‐Based Solar Cell Inspection With Autonomous Deep Learning

Mirko Kovac

Regular inspection and maintenance are crucial for ensuring the optimal performance of solar panels. However, conventional manual methods can be laborious, time consuming, and expensive, especially for large and inaccessible installations. Aerial inspectio ...

Wiley2024

Accelerating Transfer Learning with Near-Data Computation on Cloud Object Stores

Rachid Guerraoui, Diana Andreea Petrescu, Arsany Hany Abdelmessih Guirguis

Storage disaggregation underlies today's cloud and is naturally complemented by pushing down some computation to storage, thus mitigating the potential network bottleneck between the storage and compute tiers. We show how ML training benefits from storage ...

Association for Computing Machinery, Inc2024

Community-based reconstruction and simulation of a full-scale model of region CA1 of rat hippocampus

Henry Markram, Felix Schürmann, James Gonzalo King, Srikanth Ramaswamy, Juan Bautista Hernando Vieites, Alexis Arnaudon, Eilif Benjamin Muller, Michael Reimann, Huanxiang Lu, Ying Shi, Marwan Muhammad Ahmed Abdellah, Vishal Sood, Jean-Denis Georges Emile Courcol, Werner Alfons Hilda Van Geit, Lida Kanari, Michael Emiel Gevaert, Pramod Shivaji Kumbhar, Liesbeth Maria L Vanherpe, Armando Romani, Cyrille Pierre Henri Favreau, Mohameth François Sy, Judit Planas Carbonell, Genrich Ivaska, András Ecker, Alberto Antonietti, Cristina Colangelo, Anna-Kristin Kaufmann, Julian Martin Budd, Thomas Brice Delemontex, Davide Bella, Fabien Petitjean, Nadir Roman Guerrero, Mustafa Kerem Kurban, Joni Henrikki Herttuainen, Pranav Rai, Elvis Boci

The CA1 region of the hippocampus is one of the most studied regions of the rodent brain, thought to play an important role in cognitive functions such as memory and spatial navigation. Despite a wealth of experimental data on its structure and function, i ...

2024

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360° Neural Radiance Fields

Sabine Süsstrunk, Tong Zhang, Dongqing Wang

We propose InNeRF360, an automatic system that accurately removes text-specified objects from 360 • Neural Radiance Fields (NeRF). The challenge is to effectively remove objects while inpainting perceptually consistent content for the missing regions, whic ...

IEEE2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Efficient Lung Nodule Detection via 3D Deep Learning with Shifted Convolutions

Jiancheng Yang

The high computational costs of deep convolutional neural networks hinder their deployment in real-world applications, including pulmonary nodule detection from CT scans where large 3D image sizes amplify the issue. This paper presents a novel 3D method to ...

IEEE2023

Euclid: Identification of asteroid streaks in simulated images using deep learning

Georges Meylan, Frédéric Courbin

The material composition of asteroids is an essential piece of knowledge in the quest to understand the formation and evolution of the Solar System. Visual to near-infrared spectra or multiband photometry is required to constrain the material composition o ...

Edp Sciences S A2023

User assessment of fabric shading devices with a low openness factor

Marilyne Andersen, Jan Wienold, Caroline Karmann, Krishna Manwani

Providing adequate glare protection and a view to the outside through fabric shading devices is challenging because these two objectives require conflicting material properties for a fully lowered shading. In a semi -controlled office-like experiment invol ...

2023

Solving Non-linear Kolmogorov Equations in Large Dimensions by Using Deep Learning: A Numerical Comparison of Discretization Schemes

Nicolas Macris

Non-linear partial differential Kolmogorov equations are successfully used to describe a wide range of time dependent phenomena, in natural sciences, engineering or even finance. For example, in physical systems, the Allen-Cahn equation describes pattern f ...

SPRINGER/PLENUM PUBLISHERS2023

2D Nanosystems: Applications of 2D Semiconductors for In-Memory Computing

Guilherme Migliato Marega

Machine learning and data processing algorithms have been thriving in finding ways of processing and classifying information by exploiting the hidden trends of large datasets. Although these emerging computational methods have become successful in today's ...

EPFL2023

Toward higher-performance bionic limbs for wider clinical use

Silvestro Micera

Most prosthetic limbs can autonomously move with dexterity, yet they are not perceived by the user as belonging to their own body. Robotic limbs can convey information about the environment with higher precision than biological limbs, but their actual perf ...

NATURE RESEARCH2023

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Rachid Guerraoui, John Stephan, Nirupam Gupta, Rafaël Benjamin Pinot, Youssef Allouah

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

2023

Large-scale detection of marine debris in coastal areas with Sentinel-2

Devis Tuia, Sushen Jilla Venkatesa, Marc Conrad Russwurm

Detecting and quantifying marine pollution and macroplastics is an increasingly pressing ecological issue that directly impacts ecology and human health. Here, remote sensing can provide reliable estimates of plastic pollution by regularly monitoring and d ...

Cell Press2023

Wasserstein-Based Graph Alignment

Pascal Frossard, Hermina Petric Maretic, Mireille El Gheche

A novel method for comparing non-aligned graphs of various sizes is proposed, based on the Wasserstein distance between graph signal distributions induced by the respective graph Laplacian matrices. Specifically, a new formulation for the one-to-many graph ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

Tanja Christina Käser Jacober, Vinitra Swamy, Mirko Marras, Bahar Radmehr

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in human-centric fields. We im ...

2022

Mechanistic modelling of solar disinfection (SODIS) kinetics of Escherichia coli, enhanced with H2O2 - part 1: The dark side of peroxide

César Pulgarin, Stefanos Giannakis

The present bi-partite work describes the development and validation of a mechanistic kinetic model of SODIS E. coli inactivation, enhanced with H2O2. In this first part, the mechanism of the baseline dark phenomena is modelled. A mechanistic model involvi ...

ELSEVIER SCIENCE SA2022