Zobrazeno 1 - 10
of 1 432
pro vyhledávání: '"P, Saunier"'
We study algebraic K-theory and topological Hochschild homology in the setting of bimodules over a stable category, a datum we refer to as a laced category. We show that in this setting both K-theory and THH carry universal properties, the former def
Externí odkaz:
http://arxiv.org/abs/2411.04743
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
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
Autor:
Saunier, Victor
We show that Quillen's resolution theorem for K-theory also applies to exact $\infty$-categories. We introduce heart structures on a stable $\infty$-category, generalizing weight structures, and using resolution ideas, we show that the category of st
Externí odkaz:
http://arxiv.org/abs/2311.13836
Deep learning-based multivariate and multistep-ahead traffic forecasting models are typically trained with the mean squared error (MSE) or mean absolute error (MAE) as the loss function in a sequence-to-sequence setting, simply assuming that the erro
Externí odkaz:
http://arxiv.org/abs/2212.06653
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering, 2024
Spatiotemporal traffic data imputation is of great significance in intelligent transportation systems and data-driven decision-making processes. To perform efficient learning and accurate reconstruction from partially observed traffic data, we assert
Externí odkaz:
http://arxiv.org/abs/2212.01529
The problem of broad practical interest in spatiotemporal data analysis, i.e., discovering interpretable dynamic patterns from spatiotemporal data, is studied in this paper. Towards this end, we develop a time-varying reduced-rank vector autoregressi
Externí odkaz:
http://arxiv.org/abs/2211.15482
Autor:
Carole Faviez, Xiaoyi Chen, Nicolas Garcelon, Mohamad Zaidan, Katy Billot, Friederike Petzold, Hassan Faour, Maxime Douillet, Jean-Michel Rozet, Valérie Cormier-Daire, Tania Attié-Bitach, Stanislas Lyonnet, Sophie Saunier, Anita Burgun
Publikováno v:
BMC Medical Informatics and Decision Making, Vol 24, Iss 1, Pp 1-12 (2024)
Abstract Background There are approximately 8,000 different rare diseases that affect roughly 400 million people worldwide. Many of them suffer from delayed diagnosis. Ciliopathies are rare monogenic disorders characterized by a significant phenotypi
Externí odkaz:
https://doaj.org/article/38d44f5fef63446fa67280a097ada0d1
Autor:
Saunier, Victor
Publikováno v:
Ann. K-Th. 8 (2023) 609-643
We prove a generalization of the fundamental theorem of algebraic K-theory for Verdier-localizing functors by extending the proof for algebraic K-theory of spaces to the realm of stable $\infty$-categories. The formula behaves much better for Karoubi
Externí odkaz:
http://arxiv.org/abs/2209.05818
Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action recognitio
Externí odkaz:
http://arxiv.org/abs/2204.08671