- A new paper has been ACCEPTED in the conference IWBBIO-2022 (International Work-Conference on Bioinformatics and Biomedical Engineering): Akrem Sellami, Sabeur Aridhi, Salvatore Tabbone, and Marie-Dominique Devignes: « A semi-supervised graph deep learning for automatic protein function annotation »
- A new paper has been submitted to the International Conference in Image Processing (ICIP) 2022: Akrem Sellami, and Salvatore Tabbone: « BTS-3DNet: Brain Tumor Segmentation of MRI images with multi-modal 3-D deep representation learning networks »
- A new paper has been submitted to the International Conference on Pattern Recognition (ICPR) 2022: Maroua Mehri, Akrem Sellami, and Salvatore Tabbone: « Combining Multi-channel Gabor Filters and 2D-Stacked Deep Neural Networks for Historical Document Image Segmentation »
- A new paper has been published in Pattern Recognition Journal : Akrem Sellami, and Salvatore Tabbone: « Deep neural networks-based relevant latent representation learning for hyperspectral image classification »[link][ IF: 7.740](Q1). [RANK A*]
- A new paper has been published at the VISAPP conference: Refka Hanachi, Akrem Sellami, and Imed Farah: « Interpretation of Human Behavior from Multi-modal Brain MRI Images based on GRaph Deep Neural Networks and Attention Mechanism » [link] [RANK B]
- A new paper has been accepted at the International Conference on Document Analysis and Recognition (ICDAR 2021) :Akrem Sellami, and Salvatore Tabbone: « EDNets: Deep Feature Learning for Document Image Classification based on Multi-view Encoder-Decoder Neural Networks »[link] [RANK A]
- A new paper has been submitted to the Pattern Recognition Letters Journal :Akrem Sellami, Mohamed Farah, and Dulla Mauro Mura: « HCNet: A semi-supervised hypergraph convolutional networks and feature selection for hyperspectral image classification »
- A new paper has been accepted at the IEEE International Conference on Pattern Recognition (ICPR 2020) :Akrem Sellami, and Salvatore Tabbone, « Video Semantic Segmentation Using Deep Multi-View Representation Learning »[link] [RANK A]
- A new paper has been published in Pattern Recognition Letters Journal : « Fused 3-D spectral-spatial deep neural networks and spectral clustering for hyperspectral image classification » (Apr 04, 2019) [link][ IF: 3.25 ](Q1)
- A new paper has been published at the IEEE International Joint Conference on Neural Networks (IJCNN 2020) :« Mapping individual differences in cortical architecture using multi-view representation learning »[link] [RANK A]
- New paper published in Expert Systems with Applications Journal: « Hyperspectral Imagery Classification based on Semi-Supervised 3-D Deep Neural Network and Adaptive Band Selection » (Apr 04, 2019) [link][ IF: 4.29 ](Q1)
- New paper published in IEEE JSTARS Journal: « Hyperspectral Imagery Semantic Interpretation based on Adaptive Constrained Band Selection and Knowledge Extraction Techniques » (2018) [link][IF: 3.39 ](Q1)
Research Area
Research Area
My research area include machine learning, deep learning, graph representation learning, and feature extraction as well as applications to computer vision (MRI analysis, brain tumor segmentation, hyperspectral image classification,…).
Biography
Akrem Sellami is currently a Teaching and Research Assistant (ATER) at Telecom Nancy (LORIA Laboratory). He was a Postdoctoral Researcher at the LORIA laboratory between June 2020 and June 2021. The research work focuses on deep learning and graph deep representation learning for medical/satellite images analysis.
He was a Postdoctoral Researcher of the Qarma (Machine Learning Team), which is situated within the Systems and Computer Science Laboratory (Laboratoire d’Informatique et Systèmes, a.k.a. LIS), Aix-Marseille University (AMU). The work of the postdoc is carried out jointly with the Banco (Neural Bases of Communication) team, Institute of Neuroscience of Timone (Institut de Neurosciences de la Timone a.k.a. INT ). This project is funded by the Institute of Language, Communication and the Brain (ILCB)
Post-doc research focuses on understanding the relationship between brain and behavior using machine learning models (deep learning, graph Kernels, multi-view learning) and multi-modal brain images.
Since Oct. 2017, he was a Teaching Assistant (ATER) at IUT Institute, Paris Descartes University. He received the Ph.D degree in Signal, Image, Vision (SIV) from the University of Bretagne Loire, IMT Atlantique, in 2017. From 2014, he enjoyed a research scholarship at the Image and Information Processing department (ITI) at Telecom Bretagne.
He teaches various aspects of Deep Learning, Computer Science, Data Science, Graph Theory, and Computer Systems.
His current research include deep learning, artificial intelligence, multiview learning, functional data analysis, hyperspectral image analysis, and neuroscience.
