Publications associées (32)

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

Alexandre Massoud Alahi, Taylor Ferdinand Mordan

Pedestrians are arguably one of the most safety-critical road users to consider for autonomous vehicles in urban areas. In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes from a single image. The ...
2021

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

Alexandre Massoud Alahi, Taylor Ferdinand Mordan

Pedestrians are arguably one of the most safety-critical road users to consider for autonomous vehicles in urban areas. In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. These encompass visual ...
IEEE2020

Learning Task Priorities from Demonstrations

Sylvain Calinon

As humanoid robots become increasingly popular, learning and control algorithms must take into account the new constraints and challenges inherent to these platforms, if we aim to fully exploit their potential. One of the most prominent of such aspects is ...
2019

UAV-Based Situational Awareness System Using Deep Learning

Wenlong Deng

Situational awareness by Unmanned Aerial Vehicles (UAVs) is important for many applications such as surveillance, search and rescue, and disaster response. In those applications, detecting and locating people and recognizing their actions in near real-time ...
2019

How to quantify student's regularity?

Pierre Dillenbourg, Kshitij Sharma, Lukasz Kidzinski, Mina Shirvani Boroujeni, Lorenzo Lucignano

Studies carried out in classroom-based learning context, have consistently shown a positive relation between students' conscientiousness and their academic success. We hypothesize that time management and regularity are main constructing blocks of students ...
Springer2016

A Motion Capture Study to Measure the Feeling of Synchrony in Romantic Couples and in Professional Musicians

Pierre Magistretti, Delphine Preissmann, Joan Llobera Mahy

The feeling of synchrony is fundamental for most social activities and prosocial behaviors. However, little is known about the behavioral correlates of this feeling and its modulation by intergroup differences. We previously showed that the subjective feel ...
Frontiers Research Foundation2016

Intensive travel time: an obligation or a choice?

Stéphanie Vincent

This paper explores what prompts some individuals to spend a significant amount of time travelling. In the literature, travel time tends to be regarded as useless, unproductive time and, in some cases, as the worst time of the day. The actual behaviour of ...
Springer2016

Distributed learning over multitask networks with linearly related tasks

Ali H. Sayed, Roula Nassif

In this work, we consider distributed adaptive learning over multitask mean-square-error (MSE) networks where each agent is interested in estimating its own parameter vector, also called task, and where the tasks at neighboring agents are related according ...
IEEE2016

Real-time full body motion imitation on the COMAN humanoid robot

Auke Ijspeert, Florin Dzeladini, Jesse van den Kieboom

On-line full body imitation with a humanoid robot standing on its own two feet requires simultaneously maintaining the balance and imitating the motion of the demonstrator. In this paper we present a method that allows real-time motion imitation while main ...
Cambridge Univ Press2015

Scaling Up Concurrent Main-Memory Column-Store Scans: Towards Adaptive NUMA-aware Data and Task Placement

Anastasia Ailamaki, Iraklis Psaroudakis

Main-memory column-stores are called to efficiently use modern non-uniform memory access (NUMA) architectures to service concurrent clients on big data. The efficient usage of NUMA architectures depends on the data placement and scheduling strategy of the ...
2015

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.