| 2026 | ICAART | NeuroSync-Agent: A Real-Time Multimodal Fusion and LLM Reasoning Framework for Cognitive-State Inference. | Basma Jalloul, Bassem Bouaziz, Siwar Chaabene, Walid Mahdi |
| 2025 | ICONIP | Quantifying Motor Adaptation: A Hybrid AI Approach for Interpreting Short-Term Gait Variability. | Basma Jalloul, Bassem Bouaziz, Walid Mahdi, Achraf Ammar, Wolfgang Immanuel Schllhorn |
| 2021 | ICONIP | PhenoDeep: A Deep Learning-Based Approach for Detecting Reproductive Organs from Digitized Herbarium Specimen Images. | Abdelaziz Triki, Bassem Bouaziz, Jitendra Gaikwad, Walid Mahdi |
| 2018 | KES | A novel keyword rescoring method for improved spoken keyword spotting. | Ilyes Rebai, Yassine Ben Ayed, Walid Mahdi |
| 2017 | AICCSA | Content Video Browsing Based on Text Regions Extraction and Classification Using Convolutional Neural Network. | Bassem Bouaziz, Jihen Amara, Walid Mahdi |
| 2017 | AICCSA | Improving of Open-Set Language Identification by Using Deep SVM and Thresholding Functions. | Ilyes Rebai, Yassine Ben Ayed, Walid Mahdi |
| 2017 | KES | Improving speech recognition using data augmentation and acoustic model fusion. | Ilyes Rebai, Yassine Benayed, Walid Mahdi, Jean-Pierre Lorr |
| 2016 | CIBCB | A Bayesian approach to construct Context-Specific Gene Ontology: Application to protein function prediction. | Hasna Njah, Salma Jamoussi, Walid Mahdi, Mohamed Elati |
| 2016 | IJCNN | Semi-hierarchical nave Bayes classifier. | Hasna Njah, Salma Jamoussi, Walid Mahdi |
| 2016 | IJCNN | Deep kernel-SVM network. | Ilyes Rebai, Yassine Ben Ayed, Walid Mahdi |
| 2015 | ACIVS | Unified System for Visual Speech Recognition and Speaker Identification. | Ahmed Rekik, Achraf Ben-Hamadou, Walid Mahdi |
| 2015 | ACIVS | Human Machine Interaction via Visual Speech Spotting. | Ahmed Rekik, Achraf Ben-Hamadou, Walid Mahdi |
| 2015 | AICCSA | Deep architecture using Multi-Kernel Learning and multi-classifier methods. | Ilyes Rebai, Yassine Ben Ayed, Walid Mahdi |
| 2015 | ICTAI | A New Equilibrium Criterion for Learning the Cardinality of Latent Variables. | Hasna Njah, Salma Jamoussi, Walid Mahdi, Afif Masmoudi |
| 2015 | SEKE | Image retrieval based on structural and textual context. | Sana Fakhfakh, Mohamed Tmar, Walid Mahdi |
| 2014 | ATSIP | Hypovigilance detection by calculating and analyzing a spatio-temporal features of the face components based on 3D head orientation. | Belhassen Akrout, Walid Mahdi |
| 2014 | WEBIST | Multimedia Retrieval based on Geometric Distance in Semi-structured Document. | Sana Fakhfakh, Mohamed Tmar, Walid Mahdi |
| 2011 | ICIAP | A Video Grammar-Based Approach for TV News Localization and Intra-structure Identification in TV Streams. | Tarek Zlitni, Walid Mahdi, Hanne Ben-Abdallah |
| 2009 | IDEAL | Hand Localization and Fingers Features Extraction: Application to Digit Recognition in Sign Language. | Ahmed Ben Jmaa, Walid Mahdi, Yousra Ben Jemaa, Abdelmajid Ben Hamadou |
| 2009 | MOMM | A spatiotemporal text localization and identification approach for content-based video browsing. | Bassem Bouaziz, Walid Mahdi, Tarek Zlitni, Abdelmajid Ben Hamadou |
| 2009 | MOMM | A new approach for TV program identification based on video grammar. | Tarek Zlitni, Walid Mahdi, Hanne Ben-Abdallah |
| 2007 | ICIAP | Colour and Geometric based Model for Lip Localisation: Application for Lip-reading System. | Salah Werda, Walid Mahdi, Abdelmajid Ben Hamadou |