Biography

Mohamed Amine Marnissi is a research engineer and freelancer with a Ph.D. in computer vision and artificial intelligence. I received my engineering degree in computer science and a master's degree in artificial intelligence and computer vision. I has developed expertise in deep learning and computer vision, working on research projects using deep learning to address complex problems in computer vision such as object detection, face recognition, and surveillence robotic vision. I has published articles in scientific journals and presented his work at conferences and workshops.

Publications

• 

  GAN-based Vision Transformer for High-Quality Thermal Image Enhancement
  Mohamed Amine Marnissi, Abir Fathallah
  Computer Vision and Pattern Recognition Workshop (CVPRW)

  • [PDF]
  • [Project Page]
  • [BibTeX]

  @InProceedings{Marnissi_2023_CVPR,
                                      author    = {Marnissi, Mohamed Amine and Fathallah, Abir},
                                      title     = {GAN-Based Vision Transformer for High-Quality Thermal Image Enhancement},
                                      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
                                      month     = {June},
                                      year      = {2023},
                                      pages     = {817-825}
                                  }
          

• 

  Improved domain adaptive object detector via adversarial feature learning
  Mohamed Amine Marnissi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara
  Computer Vision and Image Understanding (CVIU)

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @article{marnissi2023improved,
                                      title={Improved domain adaptive object detector via adversarial feature learning},
                                      author={Marnissi, Mohamed Amine and Fradi, Hajer and Sahbani, Anis and Amara, Najoua Essoukri Ben},
                                      journal={Computer Vision and Image Understanding},
                                      pages={103660},
                                      year={2023},
                                      publisher={Elsevier}
                                    }
          

• 

  Thermal Image Enhancement using Generative Adversarial Network for Pedestrian Detection
  Mohamed Amine Marnissi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara
  25th International Conference on Pattern Recognition 2020 (ICPR)

  • [PDF]
  • [Project Page]
  • [Poster]
  • [Code]
  • [BibTeX]

  @inproceedings{marnissi2021thermal,
    title={Thermal Image Enhancement using Generative Adversarial Network for Pedestrian Detection},
    author={Marnissi, Mohamed Amine and Fradi, Hajer and Sahbani, Anis and Amara, Najoua Essoukri Ben},
    booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
    pages={6509--6516},
    year={2021},
    organization={IEEE}}
          

• 

  Unsupervised thermal-to-visible domain adaptation method for pedestrian detection
  Mohamed Amine Marnissi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara
  Pattern Recognition Letters (PRL) 2021
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @article{marnissi2021unsupervised,
    title={Unsupervised thermal-to-visible domain adaptation method for pedestrian detection},
    author={Marnissi, Mohamed Amine and Fradi, Hajer and Sahbani, Anis and Amara, Najoua Essoukri Ben},
    journal={Pattern Recognition Letters},
    year={2021},
    publisher={Elsevier}}
          

• 

  Feature distribution alignments for object detection in the thermal domain
  Mohamed Amine Marnissi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara
  The Visual Computer Journal 2022
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @article{article,
    author = {Marnissi, Mohamed and Fradi, Hajer and Sahbani, Anis and ESSOUKRI BEN AMARA, Najoua},
    year = {2022},
    month = {02},
    title = {Feature distribution alignments for object detection in the thermal domain},
    journal = {The Visual Computer}
  }
          

• 

  

  Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer
  Mohamed Amine Marnissi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara
  the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 2022
  

  • [PDF]
  • [Project Page]
  • [Code]
  • [BibTeX]

  @inproceedings{DBLP:conf/visapp/MarnissiHFSA22,
    author    = {Mohamed Amine Marnissi and Ikram Hattab and Hajer Fradi and Anis Sahbani and Najoua Essoukri Ben Amara},
    title     = {Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer},
    booktitle = {Proceedings of the 17th International Joint Conference on Computer
                 Vision, Imaging and Computer Graphics Theory and Applications, {VISIGRAPP}},
    year      = {2022}}
          

Projects

• 

  Thermal Imaging

  Thermal enhancement Generative Adversarial Network.

  Code

  

  Thermal Detection

  Development of person detection in a thermal camera.

  Code

  

  Multispectral Detection

  Development of person detection in a thermal camera.

  Code
  

  Thermal Segmentation

  Generate masks from thermal images based on ViT.

  Code

  

  Graphic Interface

  Graphical interface to analyze thermal and visible video streams.

  Code

  

  Domain Adaptation

  Detect people from thermal or visual cameras in real time.

  Code