Alexandre Alahi

Editer le profil

Professeur assistant tenure track

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

Linkedin ID

https://orcid.org/0000-0002-5004-1498

Publons - Web of Science ID

Google Scholar ID

Scopus ID

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/

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 > ENAC-DEC > DOENAC

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

vCard
Données administratives

Biographie

Alexandre Alahi is an assistant 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, 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.

Publications

Publications Infoscience

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

P. A. Kothari; A. Alahi

IEEE Transactions on Intelligent Transportation Systems. 2023-01-18. DOI : 10.1109/TITS.2022.3233906.

Alexandre Alahi

Professeur assistant tenure track

Biographie

Publications

Publications Infoscience

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

Confidence Matters: Applications to Semantic Segmentation

Automated Human Motion Analysis and Synthesis

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

Composite Relationship Fields with Transformers for Scene Graph Generation

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

Training traffic light behavior with end-to-end learning

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

Deep Learning Methods for Socially-Aware Human Trajectory Forecasting

Advancing the Adaptability of Compliant Robot Controllers for Exploration, Interaction, and Manipulation

Visual Scene Understanding for Transportation: From Detecting Objects To Relationships

Unsupervised Visual Entity Abstraction towards 2D and 3D Compositional Models

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

Bridging the gap between model-driven and data-driven methods in the era of Big Data

Towards real-world biomechanical analysis of performance and functional capacity using wearable sensors

Efficient Transformer-Based Speech Recognition

Multivariate time series forecasting for freeway networks

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

Robustness and invariance properties of image classifiers

Pedestrian 3D Bounding Box Prediction

Are socially-aware trajectory prediction models really socially-aware?

Simple Yet Effective Action Recognition for Autonomous Driving

Theory and application of a data-driven approach to compressive spectrometry in the assessment of neurophotic stimulation

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Learning to sample in Cartesian MRI

Reshaping Perception for Autonomous Driving with Semantic Keypoints

Vision-based Flocking in Aerial Robot Swarms

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

Learning to Represent and Reconstruct 3D Deformable Objects

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

Perceiving Humans: from Monocular 3D Localization to Social Distancing

A Shared Representation for Photorealistic Driving Simulators

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

DriverGym: Democratising Reinforcement Learning for Autonomous Driving

Keypoint Communities

Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving

Social NCE: Contrastive Learning of Socially-aware Motion Representations

Pedestrian intention prediction: A convolutional bottom-up multi-task approach

Guest Editorial: Introduction to the Special Issue on Long-Term Human Motion Prediction

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

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

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

Learning Decoupled Representations for Human Pose Forecasting

Efficient Depth-based Deep Learning Methods for Multi-Party Pose Estimation

Gradient-based Methods for Deep Model Interpretability

Damage Assessment of Stone Masonry Piers Using Imaged Surface Cracks

Dynamic control strategies for managing pedestrian flows

Architecture Exploration and Optimization of Heterogeneous Many-Core Compute and Memory Architectures with Architectural Extensions

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Deep visual Re-identification with confidence

Adaptive hot water production based on Supervised Learning

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Precise Hand Finger Width Estimation via RGB-D Data

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

Gait in real world: validated algorithms for gait periods and speed estimation using a single wearable sensor

Automatic detection of hand hygiene using computer vision technology

Pedestrian Intention Prediction: A Multi-task Perspective

Next Steps for Image Synthesis using Semantic Segmentation

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

Motion planning for CAVs in mixed traffic, a study on roundabouts

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