Home

Person

Alexandre Massoud Alahi

About
Privacy
Disclaimer

Graph Chatbot

Related publications (121)

Pedestrian 3D Bounding Box Prediction

Alexandre Massoud Alahi, Saeed Saadatnejad, Yi Zhou Ju

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 ...

2022

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

Alexandre Massoud Alahi, George Adaimi

OXFORD UNIV PRESS INC2022

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

Alexandre Massoud Alahi, Yuejiang Liu, Parth Ashit Kothari, Taylor Ferdinand Mordan, Bastien Germain C. Van Delft

Test-time training (TTT) through self-supervised learning (SSL) is an emerging paradigm to tackle distributional shifts. Despite encouraging results, it remains unclear when this approach thrives or fails. In this work, we first provide an in-depth look at ...

2021

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

Alexandre Massoud Alahi

The articles in this special section focus on long term human motion prediction. This represents a key ability for advanced autonomous systems, especially if they operate in densely crowded and highly dynamic environments. In those settings understanding a ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Deep visual Re-identification with confidence

Alexandre Massoud Alahi, George Adaimi, Sven Kreiss

Transportation systems often rely on understanding the flow of vehicles or pedestrian. Fromtraffic monitoring at the city scale, to commuters in train terminals, recent progress in sensingtechnology make it possible to use cameras to better understand the ...

2021

Social NCE: Contrastive Learning of Socially-aware Motion Representations

Alexandre Massoud Alahi, Yuejiang Liu

Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with neural networks sti ...

2021

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

Alexandre Massoud Alahi, Ismail Nejjar, Mohammadhossein Bahari

Vehicle trajectory prediction tasks have been commonly tackled from two distinct perspectives: either with knowledge-driven methods or more recently with data-driven ones. On the one hand, we can explicitly implement domain-knowledge or physical priors suc ...

2021

Keypoint Communities

Alexandre Massoud Alahi, Sven Kreiss, Duncan Zauss

2021

Adaptive hot water production based on Supervised Learning

Alexandre Massoud Alahi, Dolaana Khovalyg, Amirreza Heidari

A major challenge in the common approach of hot water generation in residential houses lies in the highly stochastic nature of domestic hot water (DHW) demand. Learning hot water use behavior enables water heating systems to continuously adapt to the stoch ...

2021

Learning Decoupled Representations for Human Pose Forecasting

Alexandre Massoud Alahi, Yuejiang Liu, Behnam Parsaeifard, Saeed Saadatnejad, Taylor Ferdinand Mordan

Human pose forecasting involves complex spatiotemporal interactions between body parts (e.g., arms, legs, spine). State-of-the-art approaches use Long Short-Term Memories (LSTMs) or Variational AutoEncoders (VAEs) to solve the problem. Yet, they do not eff ...

IEEE2021

Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving

Alexandre Massoud Alahi, Tao Yang, Xuanchi Ren

2021

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Alexandre Massoud Alahi, Parth Ashit Kothari, Sven Kreiss

Since the past few decades, human trajectory forecasting has been a field of active research owing to its numerous real-world applications: evacuation situation analysis, traffic operations, deployment of social robots in crowded environments, to name a fe ...

IEEE Institute of Electrical and Electronics Engineers2021

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

Alexandre Massoud Alahi, Sven Kreiss, Lorenzo Bertoni, Taylor Ferdinand Mordan

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 ...

IEEE2021

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

Alexandre Massoud Alahi, Taylor Ferdinand Mordan

The ability to predict pedestrian behaviour is crucial for road safety, traffic management systems, Advanced Driver Assistance Systems (ADAS), and more broadly autonomous vehicles. We present a vision-based system that simultaneously locates where pedestri ...

2021

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Alexandre Massoud Alahi, Parth Ashit Kothari

Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal distributions. In recent ...

2021

A Shared Representation for Photorealistic Driving Simulators

Alexandre Massoud Alahi, Saeed Saadatnejad, Siyuan Li, Taylor Ferdinand Mordan

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 ...

IEEE Institute of Electrical and Electronics Engineers2021

Enhancing discrete choice models with representation learning

Alexandre Massoud Alahi, Virginie Janine Camille Lurkin

In discrete choice modeling (DCM), model misspecifications may lead to limited predictability and biased parameter estimates. In this paper, we propose a new approach for estimating choice models in which we divide the systematic part of the utility specif ...

2020

Joint Human Pose Estimation and Stereo 3D Localization

Alexandre Massoud Alahi, Wenlong Deng, Sven Kreiss, Lorenzo Bertoni

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 ...

IEEE2020

Bilinear Multimodal Discriminator for Adversarial Domain Adaptation with Privileged Information

Alexandre Massoud Alahi, Taylor Ferdinand Mordan

Over the past few years, deep Convolutional Neural Networks have shown outstanding performance on semantic segmentation, which is an essential tool needed by self-driving cars to understand their environments. However, their training relies on large datase ...

2020

Automatic detection of hand hygiene using computer vision technology

Alexandre Massoud Alahi

Hand hygiene is essential for preventing hospital-acquired infections but is difficult to accurately track. The gold-standard (human auditors) is insufficient for assessing true overall compliance. Computer vision technology has the ability to perform more ...

2020

Page 4 of 7