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.

For an autonomous car, getting surprised is the worst thing that can happen. To prevent that, plenty of studies are trying to forecast traffic participants’ actions especially in an urban scene using recurrent networks. Recurrent networks are used for temp ...

We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and the representations learned by diffusion models, showing that external guidance on model intermediate representations accelerates training. We reconceptualize this paradigm by regularizing diffusion models with their own intermediate representations. Building on the observation that represent

Majority of the past research on application of machine learning (ML) in earthquake engineering focused on contrasting the predictive performance of different ML algorithms. In contrast, the emphasis of this paper is on the use of data to boost the predict ...

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 ...

Mobility in an effective and socially-compliant manner is an essential yet challenging task for robots operating in crowded spaces. Recent works have shown the power of deep reinforcement learning techniques to learn socially cooperative policies. However, ...

Estimating 3D human poses from 2D images remains challenging due to occlusions and projective ambiguity. Multi-view learning-based approaches mitigate these issues but often fail to generalize to real-world scenarios, as large-scale multi-view datasets with 3D ground truth are scarce and captured under constrained conditions. To overcome this limitation, recent methods rely on 2D pose estimation combined with 2D-to-3D pose lifting trained on synthetic data. Building on our previous MPL framework, we propose

Detecting that pedestrians are present in front of a vehicle is highly desirable to avoid dangerous traffic situations. A novel vision-based system is presented to automatically detect far-away pedestrians with low-resolution cameras mounted in vehicles gi ...

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduces computation by reusing previously computed model outputs across timesteps. Existing caching methods rely on heuristic criteria to choose cache/reuse timesteps and require extensive tuning. We address this limit

Our transportation field has recently witnessed an arms race of neural network-based trajectory predictors. While these predictors are at the core of many applications such as autonomous navigation or pedestrian flow simulations, their adversarial robustne ...

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 few. In this work, we cast the problem of human trajectory forecasting as learning a representation of human social interactions. Early works handcrafted this representation based on domain knowledge. However, social interactions in crowded environments are

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 ...

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent motion and human poses. GEM generates paired RGB and depth outputs for richer spatial understanding. We introduce autoregressive noise schedules to enable stable long-horizon generations. Our dataset is comprised of 4000+ hours of multimodal data across domains like auton

Recent traffic flow prediction methods are lacking abilities to determine predictive features. Thus, they will propagate the error in the next timestamps. In this paper, first, we assess the role of spatial and temporal features on the traffic speed predic ...

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a histor ...

How can a model learn human skeleton representations that generalize across multiple tasks in autonomous driving and intelligent transportation systems? Traditional self-supervised methods fall short by entangling spatial and temporal features, limiting their adaptability to downstream perception and behavior understanding tasks. In this paper, we introduce MotionMoCo, a novel self-supervised framework designed to decouple spatial and temporal information for robust, transferable skeleton representations. M

Our Ref.: 39418.EPF.P110PC Official file: tba December 20, 2024 - 51 - Abstract The present invention provides a system (100) for planning and/or providing control to neuro- modulation and/or neurostimulation and/or an actuator such as a brain computer interface (BCI) and/or providing a neural interface system, especially a brain-spinal-cord-interface sys- tem, the system (100) comprising: at least one input module (10) for brain signals (S), espe- cially raw brain signals (S); at least one pre-processing m

The recent advancements made in the realms of Artificial Intelligence (AI) and Artificial Intelligence of Things (AIoT) have unveiled transformative prospects and opportunities to enhance and optimize the environmental performance and efficiency of smart c ...

Automated pavement crack detection is essential for maintaining road infrastructure, yet conventional methods often face challenges such as data scarcity and reliance on manual inspection. This study integrates synthetic data generation with deep learning to address these limitations and improve the accuracy of automated crack detection. Using the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) to generate realistic pavement crack images, the U-Net segmentation model is optimized.

This paper systematically analyzes the security risks associated with artificial intelligence (AI) components in autonomous vehicles (AVs). Given the increasing reliance on AI for various AV functions, from perception to control, the potential for security ...

We propose a new content-aware image resizing scheme, "Stream Carving", which is based on the well-known seam carving method. Our algorithm may introduce larger seams in the retargeted image, i.e. seams with a width larger than one pixel, that we call "str ...

Alexandre Massoud Alahi

Chat with Graph Search

Feed-forwards meet recurrent networks in vehicle trajectory prediction

LayerSync: Self-aligning Intermediate Layers

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

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

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

RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting

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

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

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

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

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

STATNet: Spatial-temporal attention in the traffic prediction

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

Unified skeleton representation learning for autonomous driving

System for planning and/or providing neuromodulation and/or neurostimulation and method thereof

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

Data generation for asphalt pavement evaluation: Deep learning-based insights from generative models

A qualitative AI security risk assessment of autonomous vehicles

Stream Carving: an Adaptive Seam Carving Algorithm