Digital humanities
AI methods for historical photographs, archival metadata and cultural heritage collections.
CNRS Postdoctoral Researcher
Computer Vision | Multimodal AI | Visual Heritage
Mohamed Chelali
I build computer vision and multimodal AI systems for visual heritage, image time series, and large-scale visual collections.
Currently at CNRS, I work on AI methods for historical photographs and archival metadata within the Humanum PICTORIA ecosystem, connecting research prototypes with usable datasets and tools.
Research directions
Research
Spatio-temporal vision
Representations for satellite image time series, video sequences and temporal visual patterns.
Applied AI systems
Research engineering around classification, video summarization, tracking and visual descriptors.
Scientific output
Publications
This list uses the same BibTeX display approach as the original page.
Journals
Conference and Workshop Papers
National Conference and Workshop Papers
Presentations
Thesis
Research engineering
Projects
FORBIN Dataset
A collection of 62,135 digitized photographs of Victor Forbin, designed for historical image analysis and archival metadata research.
Image Colorization
Photographic colorization service using modern machine learning models based on neural networks. The project was developed during the DataScientest MLOps curriculum.
AI Helpers
A BSD-licensed Python library suite that simplifies AI development by automating tasks in machine learning, media processing and secure file management.
Documentation | OS Helper | Audio Helper | Video Helper | YT Helper | SFTP Helper
Temporal Stability
Spatio-temporal hand-crafted feature extraction for satellite image time series. The proposed method measures stability using a compression algorithm named Run Length Encoding.
PhD Thesis Template
A professional LaTeX template for writing a structured PhD thesis, with predefined environments for chapters, sections, figures, tables, citations, appendices and front matter.
Academic and applied path
Experience
Postdoctoral Researcher, CNRS
Multimodal AI for large-scale analysis of heritage photographs within the Humanum PICTORIA consortium.
Machine Learning Engineer, DataScientest
Training in automation, deployment and continuous monitoring of machine learning models in production.
AI Applied Scientist, Jellysmack
Video summarization, image captioning, tagging and visual descriptors.
Temporary Teaching and Research Associate (ATER), Universite Paris Cite
Lecturer in computer science and researcher at LIPADE.
PhD in Computer Science, Universite Paris Cite
Image time series analysis involving spatial and temporal information.
Courses and tutorials
Teaching
- Introduction to image analysis with C++ and Java.
- Introduction to programming and imperative programming with C.
- Functional programming with CAML.
- Advanced algorithms and object-oriented programming with Java.
Collaborations
Contact
Mohamed Chelali | mohamed.t.chelali@gmail.fr | GitHub | ResearchGate