Zobrazeno 1 - 10
of 10 944
pro vyhledávání: '"Bilodeau, A."'
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 annotation and computation costs. Therefore, unsupervised representation lear
Externí odkaz:
http://arxiv.org/abs/2409.05749
Neuromorphic (brain-inspired) photonics leverages photonic chips to accelerate artificial intelligence, offering high-speed and energy efficient solutions in RF communication, tensor processing, and data classification. However, the limited physical
Externí odkaz:
http://arxiv.org/abs/2407.02366
We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score betw
Externí odkaz:
http://arxiv.org/abs/2403.08018
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 obtain real-time masks. In this paper, we take inspiration from the set cov
Externí odkaz:
http://arxiv.org/abs/2403.03296
Autor:
Sabri, Khalil, Djilali, Célia, Bilodeau, Guillaume-Alexandre, Saunier, Nicolas, Bouachir, Wassim
Publikováno v:
Proceedings of the 21st Conference on Robots and Vision, 2024
Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes. To address this object detection problem, this work introduces an adapted detect
Externí odkaz:
http://arxiv.org/abs/2402.18503
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 complementary information to improve detection. Therefore, we propose
Externí odkaz:
http://arxiv.org/abs/2402.10752
Autor:
Lam, Sean, Khaled, Ahmed, Bilodeau, Simon, Marquez, Bicky A., Prucnal, Paul R., Chrostowski, Lukas, Shastri, Bhavin J., Shekhar, Sudip
Artificial intelligence (AI) has seen remarkable advancements across various domains, including natural language processing, computer vision, autonomous vehicles, and biology. However, the rapid expansion of AI technologies has escalated the demand f
Externí odkaz:
http://arxiv.org/abs/2401.16515
Autor:
Chen, Chi, Nguyen, Dan Thien, Lee, Shannon J., Baker, Nathan A., Karakoti, Ajay S., Lauw, Linda, Owen, Craig, Mueller, Karl T., Bilodeau, Brian A., Murugesan, Vijayakumar, Troyer, Matthias
High-throughput computational materials discovery has promised significant acceleration of the design and discovery of new materials for many years. Despite a surge in interest and activity, the constraints imposed by large-scale computational resour
Externí odkaz:
http://arxiv.org/abs/2401.04070
Autor:
Ye, Xi, Bilodeau, Guillaume-Alexandre
Publikováno v:
AAAI2024
Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has infinite-dimensional latent
Externí odkaz:
http://arxiv.org/abs/2312.06486
This paper presents an efficient deep neural network model for diagnosing Parkinson's disease from gait. More specifically, we introduce a hybrid ConvNet-Transformer architecture to accurately diagnose the disease by detecting the severity stage. The
Externí odkaz:
http://arxiv.org/abs/2311.03177