Alexandre Alahi

Editer le profil

Professeur assistant tenure track

alexandre.alahi@epfl.ch +41 21 693 26 08 http://web.stanford.edu/~alahi/

EPFL ENAC IIC VITA
GC C1 383 (Bâtiment GC)
Station 18
CH-1015 Lausanne

+41 21 693 26 08
Local: GC C1 383
EPFL > ENAC > IIC > VITA

Web site: Site web: https://vita.epfl.ch/

+41 21 693 26 08
EPFL > ENAC > ENAC-SGC > SGC-ENS

vCard
Données administratives

Biographie

Alexandre Alahi is currently an Assistant Professor at EPFL. He spent five years at Stanford University as a Post-doc and Research Scientist after obtaining his Ph.D. from EPFL. His research enables machines to perceive the world and make decisions in the context of transportation problems and smart environments. He has worked on the theoretical challenges and practical applications of socially-aware Artificial Intelligence, i.e., systems equipped with perception and social intelligence. He was awarded the Swiss NSF early and advanced researcher grants for his work on predicting human social behavior. He won the CVPR Open Source Award (2012) for his work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for his sparsity-driven algorithm that has tracked more than 100 million pedestrians to date. His research has been covered internationally by BBC, abc, PBS, Euronews, Wall street journal, and other national news outlets around the world. Alexandre has also co-founded multiple startups such as Visiosafe, and won several startup competitions. He was elected as one of the Top 20 Swiss Venture leaders in 2010.

Publications

Publications Infoscience

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

A. Carlier; M. Danelljan; A. Alahi; R. Timofte

2020-09-29. NeurIPS 2020 34th Conference on Neural Information Processing Systems, Vancouver, Canada, December 6-12, 2020.

Alexandre Alahi

Professeur assistant tenure track

Biographie

Publications

Publications Infoscience

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Precise Hand Finger Width Estimation via RGB-D Data

MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization

Uncertainty-aware Model Inversion Networks

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Joint Human Pose Estimation and Stereo 3D Localization

Collaborative Sampling in Generative Adversarial Networks

A Reinforcement Learning Approach to Train Routing and Scheduling

The electric autonomous dial-a-ride problem

Mutual Understanding in Educational Human-Robot Collaborations

Bilinear Multimodal Discriminator for Adversarial Domain Adaptation with Privileged Information

An Institutional Approach to Normative Distributed Robotics for Mixed Societies of Humans and Robots

Trustworthy Face Recognition: Improving Generalization of Deep Face Presentation Attack Detection

Learning stereo reconstruction with deep neural networks

Enhancing discrete choice models with representation learning

Learning online combinatorial stochastic policies with deep reinforcement

Automatic Differentiation in Social Force Models

Adversarial Loss for Human Trajectory Prediction

Convolutional Relational Machine for Group Activity Recognition

MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

PifPaf: Composite Fields for Human Pose Estimation

Next Steps for Social Force with Big Data

Feed-forwards meet recurrent networks in vehicle trajectory prediction

A computer vision system for deep learning-based detection of patient mobilization activities in the ICU

A Computer Vision System to Detect Bedside Patient Mobilization

Graph-based image representation learning

Pedestrian Image Generation for Self-driving Cars

Deep Visual Re-Identification with Confidence

Training Algorithms for Multiple Object Tracking

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Enhancing Discrete Choice Models with Neural Networks

Learning nuisances to track pedestrians in autonomous vehicles

Linear Artificial Forces for Human Dynamics in Complex Contexts

Learning nuisances to track pedestrians in autonomous vehicles

Congestion and departure time choice equilibrium in urban road networks

Micro-mechanical finite element modeling for in-plane behavior of historical masonry

CAR-Net: Clairvoyant Attentive Recurrent Network

Variational Methods for Human Modeling

Long-term path prediction in urban scenarios using circular distributions

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

Dealing with Correlations in Discrete Choice Models

Vision-Based Prediction of ICU Mobility Care Activities using Recurrent Neural Networks

Viewpoint Invariant Convolutional Networks for Identifying Risky Hand Hygiene Scenarios

Unsupervised Camera Localization in Crowded Spaces

Learning to Predict Human Behavior in Crowded Scenes

Tracking millions of humans

Jointly Learning Energy Expenditures and Activities using Egocentric Multimodal Signals

Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition

Unsupervised Learning of Long-Term Motion Dynamics for Videos

Towards Vision-Based Smart Hospitals: A System for Tracking and Monitoring Hand Hygiene Compliance

Characterizing and Improving Stability in Neural Style Transfer

Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies

Vision-Based Hand Hygiene Monitoring in Hospitals

Social LSTM: Human Trajectory Prediction in Crowded Spaces

Recurrent Attention Models for Depth-Based Person Identification

Point-based Path Prediction from Polar Histograms

Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes

Towards Viewpoint Invariant 3D Human Pose Estimation

Knowledge Transfer for Scene-specific Motion Prediction

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Learning to Track: Online Multi-object Tracking by Decision Making

RGB-W: When Vision Meets Wireless

Biologically Inspired Keypoints

Socially-Aware Large-Scale Crowd Forecasting

System and method for media library navigation and recommendation

Robust Real-time Pedestrians Detection in Urban Environments with a Network of Low Resolution Cameras

From Bits to Images: Inversion of Local Binary Descriptors

Beyond Bits: Reconstructing Images from Local Binary Descriptors

Foreground Silhouette Extraction robust to Sudden Changes of background Appearance

FREAK: Fast Retina Keypoint

SCOOP: A Real-Time Sparsity Driven People Localization Algorithm

Vision-Based Scene Understanding with Sparsity Promoting Priors

Sparsity Driven People Localization with a Heterogeneous Network of Cameras

Method and system for automatic objects localization

Stream Carving: an Adaptive Seam Carving Algorithm