Alexandre Massoud Alahi

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Vehicle trajectory prediction is nowadays a fundamental pillar of self-driving cars. Both the industry and research communities have acknowledged the need for such a pillar by providing public benchmarks. While state-of-the-art methods are impressive, i.e. ...

Local Binary Descriptors are becoming more and more popular for image matching tasks, especially when going mobile. While they are extensively studied in this context, their ability to carry enough information in order to infer the original image is seldom ...

Monocular and stereo visions are cost-effective solutions for 3D human localization in the context of self-driving cars or social robots. However, they are usually developed independently and have their respective strengths and limitations. We propose a no ...

Deep heteroscedastic regression models the mean and covariance of the target distribution through neural networks. The challenge arises from heteroscedasticity, which implies that the covariance is sample dependent and is often unknown. Consequently, recen ...

Forecasting pedestrian behaviors is essential for autonomous vehicles to ensure safety in urban scenarios. Previous works addressed this problem based on motion alone, omitting several additional behavioral cues helping understanding pedestrians’ true intentions. We address the problem of forecasting pedestrian actions through joint reasoning about pedestrians’ past behaviors and their surrounding environments. For this, we propose a Transformer-based feature fusion approach, where multi-modal inputs about

Forecasting pedestrians' future motions is essential for autonomous driving systems to safely navigate in urban areas. However, existing prediction algorithms often overly rely on past observed trajectories and tend to fail around abrupt dynamic changes, s ...

In order to be globally deployed, autonomous cars must guarantee the safety of pedestrians. This is the reason why forecasting pedestrians' intentions sufficiently in advance is one of the most critical and challenging tasks for autonomous vehicles. This w ...

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast vi ...

This study aims to comprehensively explore the complexities of integrating Artificial Intelligence (AI) into Autonomous Vehicles (AVs), examining the challenges introduced by AI components and their impact on testing procedures. The research focuses on ess ...

In this chapter, we present all the technical details that lead to successfully understanding the mobility of more than a hundred million individuals in crowded train terminals over the course of two years. We cover the full spectrum of an intelligent system that detects and tracks humans in high density crowds using a camera network. We share detailed insights on how to address the occlusion problem with sparsity promoting priors and discrete combinatorial optimization that models social interactions.

Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and fine-grained pre ...

In urban or crowded environments, humans rely on eye contact for fast and efficient communication with nearby people. Autonomous agents also need to detect eye contact to interact with pedestrians and safely navigate around them. In this paper, we focus on eye contact detection in the wild, i.e., real-world scenarios for autonomous vehicles with no control over the environment or the distance of pedestrians. We introduce a model that leverages semantic keypoints to detect eye contact and show that this high

We present an end-to-end trainable Neural Network architecture for stereo imaging that jointly locates and estimates human body poses in 3D. Our method defines a 2D pose for each human in a stereo pair of images and uses a correlation layer with a composit ...

A generic approach is presented to detect and track people with a network of fixed and omnidirectional cameras given severely degraded foreground silhouettes. The problem is formulated as a sparsity constrained inverse problem. A dictionary made of atoms representing the presence of a person at a given location is used within the problem formulation. A re- weighted scheme is considered to better approximate the sparsity prior. Although the framework is generic to any scene, the focus of this paper is to eva

Sensing and projecting an individual’s human thermal comfort in buildings is a complex but crucial task for transitioning toward human-centered indoor climate control. Non-intrusive collection of physiological and personal information from the human body, ...

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this approach and intr ...

Traffic forecasting has been a fundamental task in transportation research, with many methods and datasets mainly based on highway loop detector data. In recent years, drones have become a favorable choice for urban traffic monitoring, due to their flexibility, high data quality and larger spatial coverage. Although drones have promising possibilities of becoming an additional asset in traffic monitoring, the lack of public datasets and methods has made the joint use of drone and loop detector data fairly u

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots. The new method, PifPaf, uses a Part Intensity Field (PIF) to localize body parts ...

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs), providing high-fidel ...

In this paper, we propose to study the problem of localization of a dense set of people with a network of heterogeneous cameras. We propose to recast the problem as a linear inverse problem. The proposed framework is generic to any scene, scalable in the n ...

Alexandre Massoud Alahi

Chat with Graph Search

Vehicle trajectory prediction works, but not everywhere

From Bits to Images: Inversion of Local Binary Descriptors

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

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

CrossFeat: Semantic Cross-modal Attention for Pedestrian Behavior Forecasting

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

Pedestrian Intention Prediction: A Multi-task Perspective

SoccerNet 2023 challenges results

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

Tracking millions of humans

Pedestrian 3D Bounding Box Prediction

Do Pedestrians Pay Attention? Eye Contact Detection in the Wild

Joint Human Pose Estimation and Stereo 3D Localization

Sport Players Detection and Tracking With a Mixed Network of Planar and Omnidirectional Cameras

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

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

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

PifPaf: Composite Fields for Human Pose Estimation

A Shared Representation for Photorealistic Driving Simulators

Sparsity Driven People Localization with a Heterogeneous Network of Cameras