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.

Semantic Scene Completion (SSC) aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate SSC as a dense segmentation task, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a "free lunch" of SSC labels: the voxel-level class label has implicitly told the instance-level

Drones or UAVs, equipped with different sensors, have been deployed in many places especially for urban traffic monitoring or last-mile delivery. It provides the ability to control the different aspects of traffic given real-time obeservations, an important pillar for the future of transportation and smart cities. With the increasing use of such machines, many previous state-of-the-art object detectors, who have achieved high performance on front facing cameras, are being used on UAV datasets. When applied

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrim ...

We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relationsbetween individualpersons in image or video. It learns to produce an ...

The invention relates to a system and method to optimize navigation and recommendation in a distributed network of media libraries. According to the invention, it is proposed a system and a method to assist the selection of media items comprising the steps ...

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 ...

A computer implemented method measures a performance of surveillance system. A site model, a sensor model and a traffic model are selected respectively from a set of site models, a set of sensor models, and a set of traffic models to form a surveillance mo ...

We present an interpretable framework for path prediction that leverages dependencies between agents' behaviors and their spatial navigation environment. We exploit two sources of information: the past motion trajectory of the agent of interest and a wide ...

For people with limited mobility, navigating in cluttered indoor environment is challenging. In this work, we propose a mobile assistive furniture suite that is designed to ease the life of people with special needs in indoor movement. To enable intelligen ...

In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers' motives, as crucial information about the company and AI application is ...

A novel approach is presented to locate dense crowd of people in a network of fixed cameras given the severely degraded background subtracted silhouettes. The problem is formulated as a sparsity constrained inverse problem using an adaptive dictionary constructed on- line. The framework has no constraint on the number of cameras neither on the surface to be monitored. Even with a single camera, partially occluded and grouped people are correctly detected and segmented. Qualitative results are presented in i

Imitation learning for end-to-end driving trains policies only on expert demonstrations. Once deployed in a closed loop, such policies lack recovery data: small mistakes cannot be corrected and quickly compound into failures. A promising direction is to generate alternative viewpoints and trajectories beyond the logged path. Prior work explores photorealistic digital twins via neural rendering or game engines, but these methods are prohibitively slow and costly, and thus mainly used for evaluation. In this

Vision-based background subtraction algorithms model the intensity variation across time to classify a pixel as foreground. Unfortunately, such algorithms are sensitive to appearance changes of the background such as sudden changes of illumination or when ...

The transition towards a human-centered indoor climate is beneficial from occupants’ thermal comfort and from an energy reduction perspective. However, achieving this goal requires the knowledge of the thermal state of individuals at the level of body part ...

Understanding dynamic 3D environments is essential for safe autonomous driving, particularly when reasoning about human-centric, nonrigid agents. However, existing self-supervised occupancy prediction frameworks predominantly assume rigid-body motion and rely on simple frame-to-frame offsets, limiting their ability to capture fine-grained deformations and maintain temporal coherence. To address this issue, we propose DeGO, a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation

Detecting and tracking people in scenes monitored by cameras is an important step in many application scenarios such as surveillance, urban planning or behavioral studies to name a few. The amount of data produced by camera feeds is so large that it is als ...

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 ...

Vehicle trajectory prediction has increasingly relied on datadriven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain underexplored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, e.g., in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets,

We propose to evaluate our sparsity driven people localization framework on crowded complex scenes. The problem is recast as a linear inverse problem. It relies on deducing an occupancy vector, i.e. the discretized occupancy of people on the ground, from t ...

A method for automatic localization of objects in a mask. The method includes building a dictionary or atoms, wherein each atom models the presence of one object at one location and iteratively determining the atom of said dictionary which is best correlat ...

Alexandre Massoud Alahi

Chat with Graph Search

VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

Perceiving Traffic from Aerial Images

SoccerNet 2022 Challenges Results

Convolutional Relational Machine for Group Activity Recognition

System and method for media library navigation and recommendation

Learning Decoupled Representations for Human Pose Forecasting

System and Method for Measuring Performances of Surveillance Systems

CAR-Net: Clairvoyant Attentive Recurrent Network

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

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

A Sparsity Constrained Inverse Problem to Locate People in a Network of Cameras

RAP: 3D Rasterization Augmented End-to-End Planning

Foreground Silhouette Extraction robust to Sudden Changes of background Appearance

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

Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation

SCOOP: A Real-Time Sparsity Driven People Localization Algorithm

Bilinear Multimodal Discriminator for Adversarial Domain Adaptation with Privileged Information

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

Sparsity-driven People Localization Algorithm: Evaluation in Crowded Scenes Environments

Method and system for automatic objects localization