Publications

• ART

Boosting hyperspectral image classification with Gate-Shift-Fuse mechanisms in a novel CNN-Transformer approach

Mohamed Fadhlallah Guerri, Cosimo Distante, Paolo Spagnolo, Abdelmalik Taleb-Ahmed

Hyperspectral Image (HSI) classification categorizes every pixel sample into distinct land-cover types. While CNN-based methods have demonstrated significant advances in feature representation, they often struggle with extracting deep features. On the other hand, transformer models excel in…

Computers and Electronics in Agriculture, 2025, 237, Part A, pp.110489. ⟨10.1016/j.compag.2025.110489⟩. ⟨hal-05123205⟩

• ART

Polymer-Based Microstructured Photonic Membrane for Passive Heating Textiles

Mohamed Boutghatin, Salim Assaf, Pascal Tilmant, Parastesh Pirasteh-Charrier, Bahram Djafari-Rouhani, Petr Janíček, Petr Nemec, Joël Charrier, V. Thomy, Yan Pennec, Michèle Carette

The development of textiles for personal thermal management is one of the most promising technological solutions to reduce the energy consumption in heating, ventilation, and air conditioning (HVAC) systems. These technologies offer a potentially low-cost solution that can help to limit greenhouse…

ACS Omega, 2025, 10 (36), pp.40922-40929. ⟨10.1021/acsomega.5c02006⟩. ⟨hal-05294684⟩

• ART

Chemical Control for the Morphogenesis of Conducting Polymer Dendrites in Water

Antoine Baron, Corentin Scholaert, David Guérin, Yannick Coffinier, Fabien Alibart, Sébastien Pecqueur

Conducting polymer dendrite (CPD) morphogenesis is an electrochemical process that enables in materio evolving intelligence in wetware devices. During CPD morphogenesis, voltage transients drive the physical evolution of electrically conductive...

RCS Applied Polymers, 2025, ⟨10.1039/D5LP00225G⟩. ⟨hal-05344352⟩

• ART

All‐in‐One Analog AI Hardware: On‐Chip Training and Inference with Conductive‐Metal‐Oxide/HfO_x ReRAM Devices

Donato Francesco Falcone, Victoria Clerico, Wooseok Choi, Tommaso Stecconi, Folkert Horst, Laura Bégon‐lours, Matteo Galetta, Antonio La Porta, Nikhil Garg, Fabien Alibart, Bert Jan Offrein, Valeria Bragaglia

Analog in-memory computing is an emerging paradigm designed to efficiently accelerate deep neural network workloads. Recent advancements have focused on either inference or training acceleration. However, a unified analog in-memory technology platform-capable of on-chip training, weight retention,…

• ART

A Sub-400-nW Real-Time Event-Driven Spectrogram Extraction Unit in 28-nm FD-SOI CMOS for Keyword Spotting Application

Soufiane Mourrane, Benoit Larras, Sylvain Clerc, Andreia Cathelin, Antoine Frappé

Considering the power-hungry nature of speech processing, a keyword spotting (KWS) unit, used to detect multiple spoken words, is often integrated as a front-end layer. KWS systems are always active, and thus, it is extremely important to optimize the devoted power budget. In this context, this…

IEEE Journal of Solid-State Circuits, In press, ⟨10.1109/JSSC.2024.3475948⟩. ⟨hal-04793373⟩

• COUV

Phenomena, Ideas and Mechanisms. Introducing the Essays in the History of Physics and Mathematics

Raffaele Pisano, Paolo Bussotti

A History of Physics:Phenomena, Ideas and Mechanisms Essays in Honor of Salvo D’Agostino, Springer, pp.19-28, 2025, 978-3-031-26173-2. ⟨10.1007/978-3-031-26174-9_2⟩. ⟨hal-04679501⟩

• UNDEFINED

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition

Ibtissam Saadi, Abdenour Hadid, Douglas Cunningham, Abdelmalik Taleb-Ahmed, Yassin El Hillali

Vision-Language Models (VLMs) like CLIP offer promising solutions for Dynamic Facial Expression Recognition (DFER) but face challenges such as inefficient full fine-tuning, high complexity, and poor alignment between textual and visual representations. Additionally, existing methods struggle with…

2025. ⟨hal-05033150⟩

• COUV

Lagrange’s Three Methods and Langrangean in Maxwell’s A Treatise on Electricity and Magnetism (1873)

Raffaele Pisano, Donatella Marmottini, Andrea Durlo

Pisano R. (ed). A History of Physics: Phenomena, Ideas & Mechanisms. Essays in Honor of Salvo D'Agostino, Springer, 2025, 978-3-031-26173-2. ⟨hal-04511943⟩

• ART

Measurement of surface acoustic wave attenuation in aluminum using transverse acoustic field

Dame Fall, Marc Duquennoy, Nikolay Smagin, Zakariae Oumekloul, Mohammadi Ouaftouh

This paper deals with the estimation of the attenuation of surface acoustic waves (SAWs). The proposed solution consists in measuring the displacement field transversely to the axis of propagation of the acoustic beam at several distances from the transducer, considering the entire field. Unlike…

AIP Advances, 2025, 15 (6), pp.0650026. ⟨10.1063/5.0260423⟩. ⟨hal-05150833⟩

• ART

Rethinking Attention Gated with Hybrid Dual Pyramid Transformer-CNN for Generalized Segmentation in Medical Imaging

Fares Bougourzi, Fadi Dornaika, Abdelmalik Taleb-Ahmed, Vinh Truong Hoang

Inspired by the success of Transformers in Computer vision, Transformers have been widely investigated for medical imaging segmentation. However, most of Transformer architecture are using the recent transformer architectures as encoder or as parallel encoder with the CNN encoder. In this paper, we…

Lecture Notes in Computer Science, 2025, Pattern Recognition 27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part IV, 15304, pp.243-258. ⟨10.1007/978-3-031-78128-5_16⟩. ⟨hal-04850794⟩