HAL Portal Univ-Côtedazur
Not a member yet
95391 research outputs found
Sort by
Overview of GeoLifeCLEF 2025: Plant Species Presence Prediction with Environmental and High-resolution Remote Sensing Data
No full textInternational audienceGeoLifeCLEF 2025 competition, organized as part of the LifeCLEF and FGVC workshops, challenges participants to predict plant species composition at high spatial resolution across Europe using multimodal environmental data. The task builds on a large-scale dataset that combines 5 million Presence-Only (PO) observations and approximately 100,000 standardized Presence-Absence (PA) surveys, paired with Sentinel-2 imagery, Landsat time series, climate rasters, and soil descriptors. This year's edition introduced two major challenges: a geographically shifted test set with plots from previously unseen regions with different species distribution, thereby including many rare species that are under-reported by citizen scientists. These changes increased the modeling difficulty and emphasized the need for generalization under spatial shift and class imbalance. In this paper, we summarize the task design, dataset characteristics, evaluation protocol, participant approaches, and competition results, and discuss implications for scalable species distribution modeling and biodiversity monitoring
Geographical Context Matters: Bridging Fine and Coarse Spatial Information to Enhance Continental Land Cover Mapping
No full textInternational audienceLand use and land cover mapping from Earth Observation (EO) data is a critical tool for sustainable land and resource management as, for instance, in domains like biodiversity and agricultural food production. While advanced machine learning and deep learning algorithms excel at analyzing EO imagery data, they often overlook crucial geospatial metadata information that could enhance scalability and accuracy across regional, continental, and global scales. To address this limitation, we propose BRIDGE-LC (Bi-level Representation Integration for Disentangled GEospatial Land Cover), a novel deep learning framework that explicitly integrates multi-scale geospatial information into the land cover classification process. By simultaneously leveraging fine-grained (latitude/longitude) and coarse-grained (biogeographical region) spatial information, our lightweight multi-layer perceptron architecture learns from both multi-scale information during training but only requires fine-grained information for inference, allowing it to disentangle region-specific from region-agnostic land cover features while maintaining computational efficiency comparable with standard machine learning approaches. To assess the quality of our framework, we use an open-access in-situ dataset spanning the 27 countries of the European Union and we adopt several competing classification approaches commonly considered for large-scale land cover mapping. We evaluated all the approaches through two scenarios: an extrapolation scenario in which training data encompasses samples coming from all the biogeographical regions and a leave-one-region-out scenario where samples from all the regions, except one, are employed for the training stage. Additionally, we also explore the spatial representation learned by the proposed deep learning model, highlighting a connection between its internal manifold and the geographical information used during the training stage. Our results demonstrate that integrating geospatial information improves land cover mapping performances, with the most substantial gains achieved by jointly leveraging both fine-grained and coarse-grained spatial information
Conception d’une nouvelle fibre optique microstructurée à dispersion normale pour la génération de supercontinuum à 1030 nm
No full textInternational audienceNous présentons une fibre à cristal photonique à dispersion entièrement normale et àmaintien de polarisation, optimisée pour un pompage femtoseconde à 1030 nm. Conçuepour les applications ultrarapides, elle permet une génération de supercontinuum ultrastable,couvrant une plage spectrale de 750 nm à 1300 nm
Euclid Quick Data Release (Q1). Active galactic nuclei identification using diffusion-based inpainting of Euclid VIS images
No full textInternational audienceLight emission from galaxies exhibit diverse brightness profiles, influenced by factors such as galaxy type, structural features and interactions with other galaxies. Elliptical galaxies feature more uniform light distributions, while spiral and irregular galaxies have complex, varied light profiles due to their structural heterogeneity and star-forming activity. In addition, galaxies with an active galactic nucleus (AGN) feature intense, concentrated emission from gas accretion around supermassive black holes, superimposed on regular galactic light, while quasi-stellar objects (QSO) are the extreme case of the AGN emission dominating the galaxy. The challenge of identifying AGN and QSO has been discussed many times in the literature, often requiring multi-wavelength observations. This paper introduces a novel approach to identify AGN and QSO from a single image. Diffusion models have been recently developed in the machine-learning literature to generate realistic-looking images of everyday objects. Utilising the spatial resolving power of the Euclid VIS images, we created a diffusion model trained on one million sources, without using any source pre-selection or labels. The model learns to reconstruct light distributions of normal galaxies, since the population is dominated by them. We condition the prediction of the central light distribution by masking the central few pixels of each source and reconstruct the light according to the diffusion model. We further use this prediction to identify sources that deviate from this profile by examining the reconstruction error of the few central pixels regenerated in each source's core. Our approach, solely using VIS imaging, features high completeness compared to traditional methods of AGN and QSO selection, including optical, near-infrared, mid-infrared, and X-rays
Cartographie des ethnies Bambara, Dogon, Malinke, Peul, Sarakole, Sonrai et Touareg du Mali : ancrage territorial et anthropo-socioculturel
No full textInternational audienceIn Mali spielen die dort vertretenen ethnischen Gruppen eine wichtige Rolle bei der Diversifizierung von Bräuchen und traditionellen Praktiken. Die soziale Identität des Einzelnen basiert teilweise auf der Bezugnahme auf seine ethnische Zugehörigkeit. Neben dem Familiennamen und der Sprache, die bei der Identifizierung der ethnischen Herkunft des Individuums an erster Stelle stehen, gibt es mehrere andere sichtbare Elemente, die die ethnische Zugehörigkeit charakterisieren und die Bedeutung dieser Gruppen für den soziokulturellen Reichtum und ihren Beitrag zur Entwicklung einer Nation bezeugen. Aus diesem Grund interessieren wir uns in dieser Studie für die wichtigen Aspekte des Brauchtums und seine Besonderheiten, die ihn zum Ausdruck bringenIdentitätsbindung an eine bestimmte ethnische Gruppe, um deren Rolle in der Gesellschaft zu klären. Es geht auch darum, den Wandel aufzuzeigen, der sich auf diese gewohnten Strukturen angesichts des Aufkommens der Moderne auswirkt, insbesondere angesichts der imposanten Wucht der Globalisierung der Kulturen angesichts von Lebensstilen, die die Authentizität des traditionellen Wissens ethnischer Gruppen zunehmend untergraben. Für die verwendete Methode haben wir zunächst durch umfangreiche Datenerhebung auf ethnografische Literatur zu den ethnischen Gruppen Malis zurückgegriffen. Ergänzt wird dies durch Beobachtungen, die durch eine Reihe halbdirektiver Interviews unterstützt werden, die mit zehn traditionellen Persönlichkeiten (traditioneller Kommunikator, traditioneller Häuptling, Nachbarschaftshäuptling) in Bamako, Timbuktu und Ségou durchgeführt wurden. Die Datenanalyse zeigt, dass das fortschreitende Verschwinden der kulturellen Aspekte ethnischer Gruppen eine erhebliche Herausforderung für diejenigen darstellt, die sich für den Schutz des kulturellen Erbes einsetzen.In Mali, ethnic groups play an important role in the diversification of customary and traditional practices. An individual's social identity is based in part on their ethnicity. In addition to surnames and language, which are the primary indicators of an individual's ethnic origin, there are several other visible elements that characterise ethnicity and demonstrate the importance of these groups to the socio-cultural richness and development of any nation. That is why, in this study, we focus on the important aspects of custom and its distinctive features that embody this attachment to a given ethnic group in order to clarify their roles in society. We also aim to show the changes affecting these customary structures in the face of modernity, particularly the heavy weight of cultural globalisation and lifestyles that are increasingly eroding the authenticity of traditional ethnic group knowledge. In terms of the method used, we initially drew on ethnographic literature on the ethnic groups of Mali through extensive data collection. This was supplemented by observation supported by a series of semi-structured interviews conducted with ten traditional leaders (traditional communicators, traditional chiefs, neighbourhood chiefs) in Bamako, Timbuktu and Ségou, Data analysis shows that the gradual disappearance of the cultural aspects of ethnic groups poses a significant challenge for those involved in safeguarding cultural heritage.Au Mali, les groupes ethniques présents jouent un rôle important dans la diversification des pratiques coutumières et traditionnelles. L’identité sociale de l’individu repose en partie sur la référence à son ethnie. Outre le nom de famille et la langue qui arrivent aux premiers rangs dans l’identification de l’origine ethnique de l’individu, nous avons plusieurs autres éléments visibles caractérisant l’appartenance ethnique et témoignent de l’importance de ces groupes à la richesse socioculturelle et leurs apports pour le développement de toute nation. C’est pourquoi dans cette étude, nous nous intéressons aux aspects importants de la coutume et ses traits distinctifs qui matérialisent ce rattachement identitaire à un groupe ethnique donné afin de préciser leurs rôles dans la société. Il s’agit aussi de montrer le changement qui affecte ces structures coutumières face à l’émergence de la modernité avec notamment les poids imposant de la mondialisation des cultures face aux modes des vies qui effritent de plus en plus l’authenticité de savoirs traditionnels de groupes ethniques. Pour la méthode utilisée, dans un premier temps, nous avons pris appui sur la littérature ethnographique portant sur les ethnies du Mali à travers une importante collecte de données. Celle-ci est complétée par l’observation appuyée par une série d’entretien semi directif menée auprès de dix notabilités coutumières (communicateur traditionnel, chef coutumier, chef de quartier) à Bamako, Tombouctou et Ségou, L’analyse de données relève que la disparition progressive des aspects culturels de groupes ethniques pose un défi important pour les acteurs de sauvegarde du patrimoine culturel
Curvature penalization of strongly anisotropic interfaces models and their phase-field approximation
No full textThis paper studies the effect of anisotropy on sharp or diffuse interfaces models. When the surface tension is a convex function of the normal to the interface, the anisotropy is said to be weak. This usually ensures the lower semicontinuity of the associated energy. If, however, the surface tension depends on the normal in a nonconvex way, this so-called strong anisotropy may lead to instabilities related to the lack of lower semicontinuity of the functional. We investigate the regularizing effects of adding a higher order term of Willmore type to the energy. We consider two types of problems. The first one is an anisotropic nonconvex generalization of the perimeter, and the second one is an anisotropic nonconvex Mumford-Shah functional. In both cases, lower semicontinuity properties of the energies with respect to a natural mode of convergence are established, as well as Γ-convergence type results by means of a phase field approximation. In comparison with related results for curvature dependent energies, one of the original aspects of our work is that, in the context of free discontinuity problems, we are able to consider singular structures such as crack-tips or multiple junctions
GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies
No full textInternational audienceAcross three applications: pattern exploration in latent space, text-based pattern editing, and image-to-pattern prediction. The results show that GarmentImage achieves superior performance on these applications using only simple convolutional networks.</div
FontCraft: Multimodal Font Design Using Interactive Bayesian Optimization
No full textInternational audienceCreating new fonts requires a lot of human effort and professional typographic knowledge. Despite the rapid advancements of automatic font generation models, existing methods require users to prepare pre-designed characters with target styles using font-editing software, which poses a problem for non-expert users.To address this limitation, we propose FontCraft, a system that enables font generation without relying on pre-designed characters. Our approach integrates the exploration of a font-style latent space with human-in-the-loop preferential Bayesian optimization and multimodal references, facilitating efficient exploration and enhancing user control. Moreover, FontCraft allows users to revisit previous designs, retracting their earlier choices in the preferential Bayesian optimization process. Once users finish editing the style of a selected character, they can propagate it to the remaining characters and further refine them as needed. The system then generates a complete outline font in OpenType format.We evaluated the effectiveness of FontCraft through a user study comparing it to a baseline interface. Results from both quantitative and qualitative evaluations demonstrate that FontCraft enables non-expert users to design fonts efficiently
Higher-order Monte Carlo cluster dynamics for community detection in Euclidean graphs
No full textInternational audienceWe study GIBBS distributions with competing interactions and propose a higher-order extension of the SWENDSEN–WANG dynamics that incorporates triangular bonds. The new dynamics preserves the same stationary distribution, alleviates frustration, and yields markedly better sampling. When applied to a synthetic Euclidean-graph community-detection benchmark, our algorithm outperforms existing methods
Continuum, CO and Water vapour maps of the Orion Nebula. First millimetre spectral imaging with Concerto: First millimetre spectral imaging with CONCERTO
No full textInternational audienceThe millimetre spectrum of Galactic regions and galaxies is rich in continuum and molecular lines. That diversity is mostly tackled by either broad-band photometry or high resolution heterodyne spectroscopy. We aim to map the millimetre continuum emission of Galactic regions with a spectral resolution intermediate between broad-band photometry and heterodyne spectroscopy, enabling us to quickly cover large sky areas with spectroscopy. We report observations of the Orion Nebula with the CONCERTO instrument, which was installed at the APEX telescope focal plane from April 2021 to December 2023. We find that the spectrum of Orion is dominated by dust emission with an emissivity index from 1.3 to 2.0 along with the strong CO(2-1) and HO lines which are naturally separated from the continuum, thanks to CONCERTO spectral capabilities. Many regions show a strong free-free emission as well, at lower frequencies. We demonstrate the spectral capabilities of CONCERTO at intermediate spectral resolution, with a frequency coverage from 130 to 310 GHz. A sensitivity of 200 mK is achieved in one second, for one beam and a 6 GHz frequency width, over an 18 arcmin diameter field-of-view, which is within a factor 3 of the expectations. We show that we can spectrally disentangle the continuum from the CO line emission. The slope of the millimetre continuum is line-free mapped for the first time in Orion