HWHazem Wannous

Hazem Wannous

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hazem Wannous has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Forecasting Local Surface Temperatures in a Dry Pin-On-Disc Contact Using Deep Learning

    by Nikzad Motamedi, Hazem Wannous, V. Magnier, Philippe Dufrénoy

    Predicting the evolution of local thermal fields within frictional contacts remains a major challenge in tribology, due to the multi-scale and time-dependent nature of interface transformations. In dry pin-on-disc systems, the contact interface is closed and inaccessible, making direct observation of load-bearing zones impossible during operation. This work versus transient tribological regimes. Furthermore, by modifying the normal force input, the model highlights the strong sensitivity of thermal behavior to loading conditions, suggesting a pathway toward force-based stabilization strategies and data-driven smart braking. This study provides a robust experimental-AI methodology for monitoring, predicting, and potentially controlling frictional systems where direct access to the interface is not possible.

  • Recent Advances and Trends in Learning‐Based 3D Representations

    by Adrien Schockaert, Hamid Laga, Hazem Wannous, Vincent Magnier, Guillaume Dufaye, Jean‐François Witz

    The selection of an appropriate 3D representation is a fundamental design decision that dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel‐view synthesis and rendering, shape and motion analysis, recognition, and generation. While traditional representations (e.g., meshes, point clouds and volumetric grids) remain standard outputs of 3D sensors (e.g., LiDAR and 3D scanners) and are widely used in downstream applications (e.g., editing and simulation), recent neural and primitive‐based representations (e.g., 3D Gaussian Splatting) offer compact and differentiable alternatives opening a wide range of opportunities in applications such as games, AR/VR, autonomous driving, robot navigation, and medical imaging, to name a few. The goal of this paper is to survey the main families of 3D representations from discrete explicit formats to continuous implicit fields based either on neural rendering or primitive splatting. For each type of representation, we present the general formulation and its variants, discuss its benefits and limitations, and highlight key applications. We conclude the paper by outlining the open challenges and potential directions for future research. Distinct from recent surveys that broadly cover 3D object and scene reconstruction, this paper provides a focused analysis on the evolution of 3D representations themselves. We specifically emphasize the paradigm shift toward implicit representations, offering a novel perspective on how these emerging formats fundamentally alter 3D/4D workflows.

  • Open Access

    When and Where to Touch: A Temporal Contact Prior for Text-Driven 3D Hand–Object Interaction

    by Kossi Josué Adossehoun, Hazem Wannous

    Generating realistic 3D hand–object interaction motions from text remains challenging because manipulation requires reasoning about contact as a fundamentally spatio-temporal phenomenon: a model must infer not only where the hands should interactwith the object, but also when such interactions should occur. Existing contact-aware approaches, however, typically represent contact as a static spatial cue or infer it from known object trajectories, limiting their ability to capture the temporal structure specified by language. To address this limitation, we introduce 2WT-HOI, a diffusion-based framework for text-driven hand-object interaction synthesis. At the core of our method is a Temporal Contact Prior (TCP), which predicts, for each hand, frame-wise contact activation and spatial attention over object surface regions from the input text and object features. By explicitly modeling both the timing and location of contact, TCP providesstructured spatio-temporal guidance for motion generation. We integrate this prior into a Transformer-based diffusion model, where it conditions the denoising process toward temporally coherent and spatially plausible interaction patterns while preserving motion diversity. Experiments on multiple HOI benchmarks show that 2WT-HOI generates more realistic and contact-consistent interactions, improves semantic alignment, and substantially reduces penetration artifacts across diverse manipulation scenarios.

  • GNF: Gaussian Neural Fields for Multidimensional Signal Representation and Reconstruction

    by Abelaziz Bouzidi, Hamid Laga, Hazem Wannous, Ferdous Sohel

    Neural fields have emerged as a powerful framework for representing continuous multidimensional signals such as images and videos, 3D and 4D objects and scenes, and radiance fields. While efficient, achieving high‐quality representation requires the use of wide and deep neural networks. These, however, are slow to train and evaluate. Although several acceleration techniques have been proposed, they either trade memory for faster training and/or inference, rely on thousands of fitted primitives with considerable optimization time, or compromise the smooth, continuous nature of neural fields. In this paper, we introduce Gaussian Neural Fields (GNF), a novel compact neural decoder that maps learned feature grids into continuous non‐linear signals, such as RGB images, Signed Distance Functions (SDFs), and radiance fields, using a single compact layer of Gaussian kernels defined in a high‐dimensional feature space. Our key observation is that neurons in traditional MLPs perform simple computations, usually a dot product followed by an activation function, necessitating wide and deep MLPs or high‐resolution feature grids to model complex functions. In this paper, we show that replacing MLP‐based decoders with Gaussian kernels whose centers are learned features yields highly accurate representations of 2D (RGB), 3D (geometry), and 5D (radiance fields) signals with just a single layer of such kernels. This representation is highly parallelizable, operates on low‐resolution grids, and trains in under 15 seconds for 3D geometry and under 11 minutes for view synthesis. GNF matches the accuracy of deep MLP‐based decoders with far fewer parameters and significantly higher inference throughput. The source code is publicly available at https://grbfnet.github.io/.


  • Open Access

    Online hand gesture recognition using Continual Graph Transformers

    by Rim Slama, Wael Rabah, Hazem Wannous

    Online continuous action recognition has emerged as a critical research area due to its practical implications in real-world applications, such as human-computer interaction, healthcare, and robotics. Among various modalities, skeleton-based approaches have gained significant popularity, demonstrating their effectiveness in capturing 3D temporal data while ensuring robustness to environmental variations. However, most existing works focus on segment-based recognition, making them unsuitable for real-time, continuous recognition scenarios. In this paper, we propose a novel online recognition system designed for real-time skeleton sequence streaming. Our approach leverages a hybrid architecture combining Spatial Graph Convolutional Networks (S-GCN) for spatial feature extraction and a Transformer-based Graph Encoder (TGE) for capturing temporal dependencies across frames. Additionally, we introduce a continual learning mechanism to enhance model adaptability to evolving data distributions, ensuring robust recognition in dynamic environments. We evaluate our method on the SHREC'21 benchmark dataset, demonstrating its superior performance in online hand gesture recognition. Our approach not only achieves state-of-the-art accuracy but also significantly reduces false positive rates, making it a compelling solution for real-time applications. The proposed system can be seamlessly integrated into various domains, including human-robot collaboration and assistive technologies, where natural and intuitive interaction is crucial.

  • Open Access

    A Saliency based Feature Fusion Model for EEG Emotion Estimation

    by Victor Delvigne, Antoine Facchini, Hazem Wannous, Thierry Dutoit, Laurence Ris, Jean-Philippe Vandeborre

    Among the different modalities to assess emotion, electroencephalogram (EEG), representing the electrical brain activity, achieved motivating results over the last decade. Emotion estimation from EEG could help in the diagnosis or rehabilitation of certain diseases. In this paper, we propose a dual model considering two different representations of EEG feature maps: 1) a sequential based representation of EEG band power, 2) an image-based representation of the feature vectors. We also propose an innovative method to combine the information based on a saliency analysis of the image-based model to promote joint learning of both model parts. The model has been evaluated on four publicly available datasets: SEED-IV, SEED, DEAP and MPED. The achieved results outperform results from state-of-the-art approaches for three of the proposed datasets with a lower standard deviation that reflects higher stability. For sake of reproducibility, the codes and models proposed in this paper are available at https://github.com/VDelv/Emotion-EEG.


  • Application of Rail Segmentation in the Monitoring of Autonomous Train’s Frontal Environment

    by Mohamed Amine Hadded, Ankur Mahtani, Sébastien Ambellouis, Jacques Boonaert, Hazem Wannous


  • PhyDAA: Physiological Dataset Assessing Attention

    by Victor Delvigne, Hazem Wannous, Thierry Dutoit, Laurence Ris, Jean-Philippe Vandeborre

    Attention Deficit Hyperactivity Disorder (ADHD) is the most prevalent neurodevelopmental disorder among children. It affects patients’ lives in many ways: inattention, difficulty with stimuli inhibition or motor function regulation. Different treatments exist today, but these can present side effects or are not effective for all subgroups. Neurofeedback (NF) is an innovative treatment consisting of brain activity display. NF training could consist of a virtual reality (VR) video-game in which the participant’s attention affects the game. Attention being assessed through physiological signals, one of the main steps is to design an estimator for the attention state. We present a novel framework able to record physiological signals in specific attention states and able to estimate the corresponding attention state. We propose a database composed of electroencephalography signals (EEG), and an eye-tracker labelled with a score representing the attention span for 32 healthy participants. Different features are extracted from the signals and machine learning (ML) algorithms are proposed. Our approach exhibits high accuracy for attention estimation, which corroborates a correlation between attention state and physiological signals (i.e. EEG, eye-tracking signals). The dataset has been made publicly available to promote research in the domain and we encourage other scientists to use their own approach for attention estimation.