Publicaciones

• HDR

[HDR] Architectures d’apprentissage profond pour l’analyse d’images médicales : de la modélisation à l’aide au diagnostic

Feryal Windal

L’intelligence artificielle, à travers les algorithmes d’apprentissage profond, a transformé le domaine de l’analyse visuelle assistée par ordinateur ces dernières années. Ces algorithmes ont permis d’améliorer significativement les capacités d’extraction et d’interprétation des informations...

Physique [physics]. Université de Lille, 2025. ⟨tel-05393052⟩

• Thèse

Thermal effects in fracture and decohesion phenomena : multiscale models based on Statistical Mechanics, Effets thermiques dans les phénomènes de fracture et de décohésion : modèles multi-échelles basés sur la Mécanique Statistique

Claudia Binetti

Fracture and decohesion phenomena in soft materials result from homogenized effects of complex phenomena of bond breaking and reforming at the molecular scale. Despite their diversity, several material responses in artificial and biological systems are governed by analogous complex transition..., Les phénomènes de fracture et de décohésion dans les matériaux mous résultent de la rupture et du reformage de liaisons à l’échelle moléculaire. Malgré leur diversité, plusieurs réponses des systèmes artificiels et biologiques suivent des transitions analogues, comme le repliement-dépliement des...

Micro and nanotechnologies/Microelectronics. Centrale Lille Institut; Politecnico di Bari, 2025. English. ⟨NNT : 2025CLIL0031⟩. ⟨tel-05630203⟩

• Article dans une revue

A novel embroidered textile RFID adapted rectenna for current rectification and energy transfer

Baptiste Garnier, Anthony Ozuem, Bilel Hafsi, Vladan Koncar, Kamal Lmimouni

In recent years, the rise of smart textiles has enabled the development of numerous electronic textile devices for various applications, as physiological parameters monitoring in the medical field. However, powering these devices in a way that supports increased wearability and mobility remains a...

Emerging Materials Research, 2025, pp.1-7. ⟨10.1680/jemmr.25.00055⟩. ⟨hal-05405262⟩

• Article dans une revue

New photodiodes ready to bridge optical and sub-THz communications

Emilien Peytavit

Simultaneous high-bandwidth and high-optoelectronic conversion efficiency in photodiodes is difficult to achieve. Now, researchers have demonstrated waveguide-integrated photodiodes with over 200 GHz bandwidth, 0.81 A/W responsivity and a bandwidth–efficiency product of 133.5 GHz, thus enabling...

Nature Photonics, 2025, 19 (12), pp.1279-1281. ⟨10.1038/s41566-025-01814-x⟩. ⟨hal-05397309⟩

• Autre publication scientifique

Stratégie à moyen terme, table ronde

Michel Robert, Sylvie Retailleau, Hughes Metras, Pascal Benoit, Virginie Hoel, Sandrine Beaufils, Olivier Bonnaud

Conseil d’orientation du GIP-CNFM 2025, Saint-Malo, France, 3 décembre, 2025. ⟨hal-05551781⟩

• Communication dans un congrès

Temperature and doping level effect on silicon thermal conductivity

Juan Carlos Acosta Abanto, Mélanie Brouillard, Raja Sen, Jelena Sjakste, Lorenzo Paulatto, Jérôme Saint-Martin, Nathalie Vast, J.F. Robillard, Nicolas Horny, Séverine Gomés, Pierre-Olivier Chapuis

Phonons 2025 (International Conference on Phonon Scattering in Condensed Matter), Dec 2025, Buenos Aires, Argentina. ⟨hal-05407127⟩

• Article dans une revue

Integrating perceptual quality analysis and caption-based features for robust deepfake video detection

Hessen Bougueffa Eutamene, Wassim Hamidouche, Mamadou Keita, Abdelmalik Taleb-Ahmed, Abdenour Hadid

Inspired by the benefits of both linguistic representations as well as visual quality analysis, we propose a multimodal framework for deepfake detection with reliable accuracy. Our method acquires low-level perceptual features from frames of video, including contrast, brightness, and sharpness, and...

Computers and Electrical Engineering, 2025, 128 (Part A), pp.110699. ⟨10.1016/j.compeleceng.2025.110699⟩. ⟨hal-05254097⟩

• Thèse

Improving Facial Expression Recognition in Realistic Environments Using Deep Learning Approaches, Amélioration de la reconnaissance des expressions faciales dans des environnements réalistes à l'aide d'approches d'apprentissage profond

Ibtissam Saadi

Facial expressions are vital channels of non-verbal communication, conveying rich information about emotional and cognitive states in social interactions. Enabling intelligent systems to automatically recognize these expressions makes Facial Expression Recognition (FER) a key task in affective..., Les expressions faciales sont des canaux essentiels de communication non verbale, qui transmettent de nombreuses informations sur les états émotionnels et cognitifs dans les interactions sociales. Permettre aux systèmes intelligents de reconnaître automatiquement ces expressions fait de la...

Computer Vision and Pattern Recognition [cs.CV]. Université Polytechnique Hauts-de-France; Institut national des sciences appliquées Hauts-de-France; Université de technologie de Brandebourg (Allemagne), 2025. English. ⟨NNT : ⟩. ⟨tel-05505138⟩

• Article dans une revue

A comprehensive review of facial beauty prediction using deep learning techniques

Djamel Eddine Boukhari, Fadi Dornaika, Ali Chemsa, Abdelmalik Taleb-Ahmed

<div xmlns="http://www.tei-c.org/ns/1.0"><p>Facial beauty prediction (FBP) is an emerging area of artificial intelligence (AI) that focuses on the development of models that analyze facial features to assess beauty, based on human perception. This task is particularly...

Engineering Applications of Artificial Intelligence, 2025, 161, ⟨10.1016/j.engappai.2025.112009⟩. ⟨hal-05393552⟩

• Article dans une revue

Non-linear elastic-plastic behavior of the invert glass lithium phosphorous oxynitride (LiPON)

S. Kalnaus, A.S. Westover, G.M. Veith, K.D. Owensby, Wan-Yu Tsai, T. Egami

Micro and nano-scale mechanical behavior of network/ionic glasses is dictated by their composition and the number of constraints per structural unit. From this perspective, the glass LiPON presents the opportunity for enhancement of the microscale ductility due to its rather unconstrained...

Journal of Non-Crystalline Solids, 2025, 669, pp.123793. ⟨10.1016/j.jnoncrysol.2025.123793⟩. ⟨hal-05393613⟩