output
20072025
most citedDeep Ordinal Regression Network for Monocular Depth Estimation

172 citations

60 papers

cs.LG2025

Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention

Léo Hein, Giovanni de Nunzio, Giovanni Chierchia +2

Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While f…

physics.soc-ph2024★ 17 cited

Cool Pavements

Martin Hendel

Cool pavements designate alternative pavements designed to reduce their contribution to urban heating. Urban heating generally refers to the sensible heat exchanged with the atmosp…

physics.soc-ph2024

Cartographie du confort thermique au sein d'une cours d'{é}cole parisienne : couplage de mesures microclimatiques fixes et mobiles

Ghid Karam, Maïlys Chanial, Maxime Chaumont +2

Climate change will result in more frequent, more intense and longer-lasting heat waves by 2050. As part of its Climate Plan and its resilience strategy, the City of Paris is deplo…

physics.ao-ph2024★ 1 cited

The Oasis Project: UHI mitigation strategies applied to Parisian schoolyards

Ghid Karam, Martin Hendel, Bobée Cécilia +3

Paris is experimenting and implementing strategies to increase the capital's resilience and promote climate change adaptation. Major heatwaves have been hitting the French Capital…

physics.soc-ph2024

Physical and geographic analysis of the urban cooling potential

Martin Hendel, Parison Sophie, Royon Laurent

The performance of a number of urban cooling techniques has been thoroughly studied by the scientific community. However, decision-makers lack the tools to spatialize their deploym…

physics.soc-ph2024★ 1 cited

Thermal and microclimatic behavior of OASIS schoolyard paving materials

Ghid Karam, Maïlys Chanial, Arnaud Grados +2

As part of its Resilience Strategy, the City of Paris' OASIS program aims to contribute ot its adaptation to heatwaves and climate change by transforming schoolyards into climate s…

cs.LG2023

Improving Plasticity in Online Continual Learning via Collaborative Learning

Maorong Wang, Nicolas Michel, Ling Xiao +1

Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL…

math.GR2023

Silhouettes and generic properties of subgroups of the modular group

Frédérique Bassino, Cyril Nicaud, Pascal Weil

We show that the probability for a finitely generated subgroup of the modular group, of size , to be almost malnormal or non-parabolic, tends to 0 as tends to infinity -- wh…

cs.LG2023★ 1 cited

Domain-Aware Augmentations for Unsupervised Online General Continual Learning

Nicolas Michel, Romain Negrel, Giovanni Chierchia +1

Continual Learning has been challenging, especially when dealing with unsupervised scenarios such as Unsupervised Online General Continual Learning (UOGCL), where the learning agen…

cs.LG2023

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

Nicolas Michel, Giovanni Chierchia, Romain Negrel +1

We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresp…

eess.IV2022★ 3 cited

Join, select, and insert: efficient out-of-core algorithms for hierarchical segmentation trees

Josselin Lefèvre, Jean Cousty, Benjamin Perret +1

Binary Partition Hierarchies (BPH) and minimum spanning trees are fundamental data structures involved in hierarchical analysis such as quasi-flat zones or watershed. However, clas…

cs.DC2021★ 1 cited

Distributed coloring and the local structure of unit-disk graphs

Louis Esperet, Sébastien Julliot, Arnaud de Mesmay

Coloring unit-disk graphs efficiently is an important problem in the global and distributed setting, with applications in radio channel assignment problems when the communication r…

cs.CV2021★ 10 cited

Triplet-Watershed for Hyperspectral Image Classification

Aditya Challa, Sravan Danda, B. S. Daya Sagar +1

Hyperspectral images (HSI) consist of rich spatial and spectral information, which can potentially be used for several applications. However, noise, band correlations and high dime…

math.OC2020★ 10 cited

Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance

A. Barakat, P. Bianchi, W. Hachem +1

In this paper, a general stochastic optimization procedure is studied, unifying several variants of the stochastic gradient descent such as, among others, the stochastic heavy ball…

math.OC2020★ 8 cited

Sparse Signal Reconstruction for Nonlinear Models via Piecewise Rational Optimization

Arthur Marmin, Marc Castella, Jean-Christophe Pesquet +1

We propose a method to reconstruct sparse signals degraded by a nonlinear distortion and acquired at a limited sampling rate. Our method formulates the reconstruction problem as a…

math.CO2020★ 2 cited

Three Fuss-Catalan posets in interaction and their associative algebras

Camille Combe, Samuele Giraudo

We introduce -cliffs, a generalization of permutations and increasing trees depending on a range map . We define a first lattice structure on these objects and we establish g…

math.CO2020★ 1 cited

A character approach to directed genus distribution of graphs: the bipartite single-black-vertex case

Yichao Chen, Wenjie Fang

Given an Eulerian digraph, we consider the genus distribution of its face-oriented embeddings. We prove that such distribution is log-concave for two families of Eulerian digraphs,…

math.CO2020

Duality of graded graphs through operads

Samuele Giraudo

Pairs of graded graphs, together with the Fomin property of graded graph duality, are rich combinatorial structures providing among other a framework for enumeration. The prototypi…

math.GR2020★ 4 cited

Statistics of subgroups of the modular group

Frédérique Bassino, Cyril Nicaud, Pascal Weil

We count the finitely generated subgroups of the modular group . More precisely: each such subgroup can be represented by its Stallings graph …

math.OC2020★ 28 cited

SPOQ -Over- Regularization for Sparse Signal Recovery applied to Mass Spectrometry

Afef Cherni, Emilie Chouzenoux, Laurent Duval +1

Underdetermined or ill-posed inverse problems require additional information for \ldd{d} sound solutions with tractable optimization algorithms. Sparsity yields consequent heuristi…

math.CO2020★ 2 cited

Bijective link between Chapoton's new intervals and bipartite planar maps

Wenjie Fang

In 2006, Chapoton defined a class of Tamari intervals called "new intervals" in his enumeration of Tamari intervals, and he found that these new intervals are equi-enumerated with…

cs.CC2019★ 1 cited

Hardness of Minimum Barrier Shrinkage and Minimum Installation Path

Sergio Cabello, Éric Colin de Verdière

In the Minimum Installation Path problem, we are given a graph with edge weights and two vertices of . We want to assign a non-negative power to each ver…

math.CO2019★ 10 cited

Compacted binary trees admit a stretched exponential

Andrew Elvey Price, Wenjie Fang, Michael Wallner

A compacted binary tree is a directed acyclic graph encoding a binary tree in which common subtrees are factored and shared, such that they are represented only once. We show that…

math.CA2019★ 6 cited

Absolute root separation

Yann Bugeaud, Andrej Dujella, Wenjie Fang +2

The absolute separation of a polynomial is the minimum nonzero difference between the absolute values of its roots. In the case of polynomials with integer coefficients, it can be…