Alexandre Alahi

alexandre.alahi@epfl.ch +41 21 693 26 08 https://www.epfl.ch/labs/vita/

vCard

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

+41 21 693 26 08
Office: GC C1 383
EPFL › ENAC › IIC › VITA

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

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

+41 21 693 26 08
Office: GC C1 383
EPFL › ENAC › ENAC-DEC › DOENAC

Site web: https://www.epfl.ch/schools/enac/about/diversity-office/

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

+41 21 693 26 08
Office: GC C1 383
EPFL › VPA › VPA-AVP-DLE › AVP-DLE-EDOC › EDCE-ENS

Expertise

Transportation
Mobility
Computer Vision
Machine Learning
Deep Learning
Human-Robot Interaction
Socially-aware Artificial Intelligence
Ambient Intelligence

Biographie Prix et distinctions Publications Enseignement

Alexandre Alahi is an associate professor at EPFL leading the Visual Intelligence for Transportation laboratory (VITA). Before joining EPFL in 2017, he spent multiple years at Stanford University as a Post-doc and Research Scientist.
His research lies at the intersection of Computer Vision, Machine Learning, and Robotics applied to transportation & mobility. To make Artificial Intelligence (AI) driven systems such as autonomous vehicles a safe reality, his lab works on a new type of Artificial Intelligence (AI), namely socially-aware AI, i.e., an AI augmented with social intelligence.
In 2022&2023, Alexandre was recognized as the top 100 Most Influential Scholar in Computer Vision over the past 10 years.
His research team received the editor's choice award from the journal Image and vision computing (2021) for their work on human motion prediction, the honorable mention at an ICCV workshop (2019) for their work on human pose estimation,
the CVPR Open Source Award (2012) for their work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for their sparsity-driven algorithm that has tracked more than 100 million pedestrians to date.
His work has been licensed to several companies and 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.

Prix et distinctions

CVPR Open Source Award

ICDSC Challenge Prize

AI 100 Most Influential Scholar Honorable Mention in Computer Vision

2022

AI 2000 Most Influential Scholar Honorable Mention

2022

Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness

D. Fernández Llorca; R. Hamon; H. Junklewitz; K. Grosse; L. Kunze et al.

European Transport Research Review. 2025. DOI : 10.1186/s12544-025-00732-x.

Alexandre Alahi

Expertise

Prix et distinctions

Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness

Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model

GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization

Social-Pose: Enhancing Trajectory Prediction with Human Body Pose

TAROT: Targeted Data Selection via Optimal Transport

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation

FG2 : Fine-Grained Cross-View Localization by Fine-Grained Feature Matching

Certified Human Trajectory Prediction

MotionMap: Representing Multimodality in Human Pose Forecasting

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

Principles and Guidelines for Evaluating Social RobotNavigation Algorithms

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

Position: A taxonomy for reporting and describing AI security incidents

X-ray Micro-CT based characterization of rock cuttings with deep learning

Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data

Unified Human Localization and Trajectory Prediction with Monocular Vision

Person Re-Identification and its Application to Multi-Object Tracking

Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations

Automated Detection of Isolated REM Sleep Behavior Disorder Using Computer Vision

Keypoint Promptable Re-Identification

HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario

A qualitative AI security risk assessment of autonomous vehicles

SoccerNet 2023 challenges results

Multi-Transmotion: Pre-trained Model for Human Motion Prediction

MPL: Lifting 3D Human Pose from Multi-view 2D Poses

Eye-Rubbing Detection Using a Smartwatch: A Feasibility Study Demonstrated High Accuracy With Machine Learning

CODE: Confident Ordinary Differential Editing

Towards more Practical Threat Models in Artificial Intelligence Security

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Dynamic Voxels Based on Ego-Conditioned Prediction: An Integrated Spatio-Temporal Framework for Motion Planning

JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

Social-Transmotion: Promptable Human Trajectory Prediction

When Your AI Becomes a Target: AI Security Incidents and Best Practices

Discovering meaningful units from text sequences

Predicting the long-term collective behaviour of fish pairs with deep learning

A journey toward generalizable trajectory forecasting models

Toward Reliable Human Pose Forecasting With Uncertainty

Bridging Discrete Choice Modeling and Neural Networks: Unifying Statistical Rigor and Predictive Power

Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: A comprehensive systematic review

Toward contactless human thermal monitoring: A framework for Machine Learning-based human thermo-physiology modeling augmented with computer vision

Urban Digital Twin Challenges: A Systematic Review and Perspectives for Sustainable Smart Cities

Traffic perception from aerial images using butterfly fields

Real-Time Localization for Closed-Loop Control of Assistive Furniture

On Pitfalls of Test-time Adaptation

Non-intrusive physiological parameters sensing for personalized human thermal comfort prediction

A generic diffusion-based approach for 3D human pose prediction in the wild

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

The automated collapse data constructor technique and the data-driven methodology for seismic collapse risk assessment

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

Manipulating Trajectory Prediction with Backdoors

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Confidence Matters: Applications to Semantic Segmentation

Composite Relationship Fields with Transformers for Scene Graph Generation

Training Traffic Light Behavior with End-to-End Learning

Body Part-Based Representation Learning for Occluded Person Re-Identification

Learning Robust and Adaptive Representations: from Interactions, for Interactions

1(st) Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

Proxy methods for detection of inhalation exposure in simulated office environments

Are the trajectory prediction models generalizable?

Motion Style TransferModular Low-Rank Style Transfer for Deep Trajectory Forecasting

Vehicle trajectory prediction works, but not everywhere

STATNet: Spatial-temporal attention in the traffic prediction

Automated Detection Of Isolated Rem Sleep Behavior Disorder (Irbd) During Single Night In-Lab Video-Polysomnography (Psg) Using Computer Vision

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

Pedestrian 3D Bounding Box Prediction

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Visual Scene Understanding for Transportation: From Detecting Objects To Relationships

Simple Yet Effective Action Recognition for Autonomous Driving

Reshaping Perception for Autonomous Driving with Semantic Keypoints

Detecting 32 Pedestrian Attributes for Autonomous Vehicles