collaborators

6 papers

cs.CV2026

Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations

Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau +1

Understanding and monitoring human behavior in metro stations play an important role in supporting suicide prevention efforts, where early identification of high-risk situations ca…

cs.CV2026

PMMA: The Polytechnique Montreal Mobility Aids Dataset

Qingwu Liu, Nicolas Saunier, Guillaume-Alexandre Bilodeau

This study introduces a new object detection dataset of pedestrians using mobility aids, named PMMA. The dataset was collected in an outdoor environment, where volunteers used whee…

cs.CV2026

Detection of Autonomous Shuttles in Urban Traffic Images Using Adaptive Residual Context

Mohamed Aziz Younes, Nicolas Saunier, Guillaume-Alexandre Bilodeau

The progressive automation of transport promises to enhance safety and sustainability through shared mobility. Like other vehicles and road users, and even more so for such a new t…

cs.CV2025

Dual-Stream Attention with Multi-Modal Queries for Object Detection in Transportation Applications

Noreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose…

cs.CV2025

InceptoFormer: A Multi-Signal Neural Framework for Parkinson's Disease Severity Evaluation from Gait

Safwen Naimi, Arij Said, Wassim Bouachir +1

We present InceptoFormer, a multi-signal neural framework designed for Parkinson's Disease (PD) severity evaluation via gait dynamics analysis. Our architecture introduces a 1D ada…

cs.CV2025

How good are deep learning methods for automated road safety analysis using video data? An experimental study

Qingwu Liu, Nicolas Saunier, Guillaume-Alexandre Bilodeau

Image-based multi-object detection (MOD) and multi-object tracking (MOT) are advancing at a fast pace. A variety of 2D and 3D MOD and MOT methods have been developed for monocular…