Who am I?

I am Mohamed Chelali, researcher at the crossroads of computer vision and artificial intelligence. Passionate about technological innovation and solving complex problems.

Keywords : Video Processing, Tracking, Violence Detection, Satellite Image Processing, Image Time Series, Computer Vision, Remote Sensing.

Resume in English, CV in French

Timeline

[Aug 2024 - Feb 2025] - Data Scientest

Machine Learning Ops

Training in technical skills for automation, deployment, and continuous monitoring of machine learning models in production

[2022-May] - Jellysmack

AI Applied Scientist

Designed, prototyped and put into production an engine with artificial intelligence to summarize a video.
Internal consultant for the description of images in sentences, tags and other descriptors.

[2018-2021] - Université Paris Cité

PhD in Computer Science

Thesis title : Image time series analysis involving spatial and temporal information

New constellations of satellites acquire images with a high spatial, spectral and temporal resolution around the world leading to Satellite Image Time Series (SITS). During my thesis, our objective is to analyse the image time serie in order to extract features that enrich the orginal data and perform an application, such as a classification, by maximazing the accuracy
Advisors: Nicole Vincent et Camille Kurtz

PhD defense page

[2016-2018] - Paris Descartes University

Master's degree in Computer Sciences - Image et Plurimedia field

The master's was validated with a research internship at the LIPADE.
Advisors: Nicole Vincent, Camille Kurtz.

[2015-2016] - El Bachir El Ibrahimi University

Master 1 in Computer Science - Networking and Multimedia field

[2012-2015] - El Bachir El Ibrahimi University

Bachelor's degree in Computer Science - Image Processing field

Research

@phdthesis{mchelali_PHD_2021,
        title={Prise en compte de l'information spatiale et temporelle pour l'analyse
        de séquences d'images},
        year={2021},
        month={November},
        school={Université Paris Cité (LIPADE), Funding: French national grant
        (2017-2021)},
        author={Chelali, M.},
        pdf = {articles/manuscrit_doctorat_mchelali1.pdf}
        }

@article{chelaliCVIU2020,
        author = {Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        title = {Deep-STaR: Classification of image time series based on
        spatio-temporal representations},
        booktitle = {Computer Vision and Image Understanding -- CVIU 2020},
        pages = {XX--XX},
        doi = {https://doi.org/10.1016/j.cviu.2021.103221},
        year = {2020},
        pdf = {articles/CVIU_MChelali_2020.pdf}
        }

@article{chelaliIJPRAI2020,
        author = {Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        title = {Influence of data representations and deep architectures in
        image time series classification},
        booktitle = {International Journal of Pattern Recognition and Artificial
        Intelligence -- IJPRAI 2020},
        pages = {2160001},
        year = {2020},
        pdf = {articles/IJPRAI_RandWalk_2020.pdf},
        doi={https://www.worldscientific.com/doi/abs/10.1142/S0218001421600016}
        }

@inproceedings{chelali_ICIP_2021,
        title={Violence detection from video under 2D spatio-temporal
        representations},
        year={2021},
        booktitle={IEEE International Conference on Image Processing -- ICIP
        2021},
        month={Sep},
        address={Anchorage, Alaska, USA (Virtual)},
        pages={2593-2597},
        author={Chelali, M. and Kurtz, C. and Vincent, N.},
        doi = {https://ieeexplore.ieee.org/abstract/document/9506142},
        pdf= {articles/ICIP_Violence_Detection.pdf}
        }

@inproceedings{chelali_ICPR_2020,
        title={Classification of spatially enriched pixel time series with
        convolutional neural networks},
        year={2020},
        booktitle={International Conference on Pattern Recognition -- ICPR
        2020},
        month={Jan},
        address={Milan, Italy (Virtual)},
        pages={5310--5317},
        author={Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        doi = {https://doi.org/10.1109/ICPR48806.2021.9412892},
        pdf = {articles/ICPR20.pdf}
        }

@inproceedings{chelali1_ICPRAI_2020,
        title={From pixels to Random Walk based segments for image time series
        deep classification},
        year={2020},
        booktitle={International Conference on Pattern Recognition and
        Artificial Intelligence -- ICPRAI 2020},
        month={May},
        address={Zhongshan City, China},
        pages={339--351},
        author={Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        doi={https://doi.org/10.1007/978-3-030-59830-3_30},
        pdf = {articles/ICPRAI2020_randWalk.pdf}
        }

@inproceedings{chelali2_ICPRAI_2020,
        title={Spatio-temporal stability analysis in Satellite Image Times
        Series},
        year={2020},
        booktitle={International Conference on Pattern Recognition and
        Artificial Intelligence -- ICPRAI 2020},
        month={May},
        address={Zhongshan City, China},
        pages={484--499},
        author={Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        doi={https://doi.org/10.1007/978-3-030-59830-3_42},
        pdf = {articles/ICPRAI2020_TempStab.pdf}
        }

@inproceedings{chelali_VISAPP_2020,
        title={Image time series classification based on a planar
        spatio-temporal data representation},
        year={2020},
        booktitle={International Conference on Computer Vision Theory and
        Applications -- VISAPP 2020},
        month={February},
        address={Valletta (Malta)},
        pages={276-283},
        publisher={SCITEPRESS Digital Library},
        author={Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        doi={https://doi.org/10.5220/0008949202760283},
        pdf = {articles/SCITEPRESS_Conference_Latex.pdf}
        }

@inproceedings{mchelali_2019,
        author = {Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        title = {Urban land cover analysis from satellite image time series
        based on temporal stability},
        booktitle = {Joint Urban Remote Sensing Event -- JURSE 2019, pages 1-4,
        IEEE Geoscience and Remote Sensing Society.},
        year = {2019},
        pages = {1--4},
        doi = {https://doi.org/10.1109/JURSE.2019.8808967},
        pdf = {articles/jurse2019.pdf}
        }

@NATIONALROCEEDINGS{apta2020_mchelali,
        author="Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.",
        title="Classification de séries d'images via une représentation spatio-temporelle",
        booktitle="Atelier sur l'Apprentissage Profond dans le cadre de la Conférence Extraction et Gestion des Connaissances -- APTA@EGC 2020",
        year="2020",
        pdf="https://apta2020.sciencesconf.org/data/APTA_EGC2020_actes.pdf"
        }

@NATIONALROCEEDINGS{chelali_RFIA_2020,
        title={Des pixels aux segments pour la classification de séries
        temporelles d'images via des réseaux de neurones convolutionnels},
        year={2020},
        booktitle={Proceedings of the Congrès Reconnaissance des Formes, Image,
        Apprentissage et Perception -- RFIAP 2020},
        month={July},
        address={Vannes (France)},
        pages={1-7},
        author={Chelali, M. and Kurtz, C. and Puissant, A. and Vincent, N.},
        pdf={https://cap-rfiap2020.sciencesconf.org/data/RFIAP_2020_paper_32.pdf}
        }

@misc{gdr_maclean2019Renne,
        author="Chelali, M.",
        title="Analyse de l'occupation des sols à partir de séries temporelles d'images setellitaires basée sur la sabilité temporelle",
        booktitle="MACLEAN (Machine Learning for Earth Observation Data)",
        year="27-07-2019"
        }

, .

[PDF] [BibTeX] [DOI] [URL]

Journals

Books

Conference and Workshop Papers

National conference and Workshop Papers

Presentation

Thesis

Project

Temporal stability

Spatio-temporal hand-crafted features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding.

Temporal stability code available on github

Phd Thesis Template

This LaTeX template is designed to streamline the creation of a professional and well-structured PhD thesis. It adheres to academic formatting standards while remaining highly customizable to meet the specific requirements of institutions. This template provides predefined environments for chapters, sections, figures, tables, and citations, with additional styling for the title page, table of contents, and appendices.

Template is available on github
Template is available on overleaf

Teaching

I had a teaching assignments during of my Phd research at the UFR Mathématiques et Informatique of Université Paris Cité

Introduction to image analysis (C++/JAVA programming language)
Introduction to programming (C programming language)
Imperative programming (C programming language)
Functionnal programming (CAML)

I had a teaching assignments at the IUT of Université Paris Cité

Introduction to programming(C/C++ programming language)
Advanced Algorithms (JAVA programming language)
oriented object programming (JAVA programming language)

Tutorials

Image classification using deep neural networks

Discover how to classify images step by step using deep neural networks in a beginner-friendly tutorial.