4 citations · 7 across the 15 of their papers we have counts for
4 papers · 1 filter
ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOL
Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau
To extract robust and generalizable skeleton action recognition features, large amounts of well-curated data are typically required, which is a challenging task hindered by annotat…
CenterDisks: Real-time instance segmentation with disk covering
Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau
Increasing the accuracy of instance segmentation methods is often done at the expense of speed. Using coarser representations, we can reduce the number of parameters and thus obtai…
STF: Spatio-Temporal Fusion Module for Improving Video Object Detection
Noreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this…
Detection of Micromobility Vehicles in Urban Traffic Videos
Khalil Sabri, Célia Djilali, Guillaume-Alexandre Bilodeau +2
Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes. To address…