Ridouane Ghermi
ridouane dot ghermi at inria dot fr

I am a second-year PhD student at INRIA and Ecole Polytechnique, working on long-form video understanding under the supervision of Vicky Kalogeiton and Ivan Laptev. My research focuses on advancing multimodal reasoning in video-language models, with a special focus on movies.

I hold a Master's degree in statistics from ENSAE Paris and have prior experience as a data scientist at Owkin and as a quant research intern at Capital Fund Management (CFM).

Google Scholar  /  LinkedIn  /  Twitter  /  GitHub

profile photo
News
2024-11 - Visited MBZUAI in Abu Dhabi for two weeks.
2024-07 - Attended the ICVSS Summer School in Sicily.
2024-03 - Attended the ELLIS Winter School on Foundation Models in Amsterdam.
2023-06 - Started a PhD at INRIA and Ecole Polytechnique with Vicky Kalogeiton and Ivan Laptev in Paris.
Research
sf20k Long Story Short: Story-level Video Understanding from 20K Short Films
Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, Ivan Laptev
arXiv, 2024  
arXiv / code / dataset / project page
omicsrpz Robust Evaluation of Deep Learning-based Representation Methods for Survival and Gene Essentiality Prediction on Bulk RNA-seq Data
Baptiste Gross, Antonin Dauvin, Vincent Cabeli, Virgilio Kmetzsch, Jean El Khoury, Gaetan Dissez, Khalil Ouardini, Simon Grouard, Alec Davi, Regis Loeb, Christian Esposito, Louis Hulot, Ridouane Ghermi, Michael Blum, Yannis Darhi, Eric Y. Durand, Alberto Romagnoni
Nature Scientific Reports, 2024  
arxiv / publication / project page
phikon Scaling Self-Supervised Learning for Histopathology with Masked Image Modeling
Alexandre Filiot, Ridouane Ghermi, Antoine Olivier, Paul Jacob, Lucas Fidon, Alice Mac Kain, Charlie Saillard, Jean-Baptiste Schiratti
medRxiv, 2023  
arxiv / code / project page
pulsai An artificial intelligence model predicts the survival of solid tumour patients from imaging and clinical data
Kathryn Schutte, Fabien Brulport, Sana Harguem-Zayani, Jean-Baptiste Schiratti, Ridouane Ghermi, Paul Jehanno, Alexandre Jaeger, Talal Alamri, Raphaël Naccache, Leila Haddag-Miliani, Teresa Orsi, Jean-Philippe Lamarque, Isaline Hoferer, Littisha Lawrance, Baya Benatsou, Imad Bousaid, Mikael Azoulay, Antoine Verdon, François Bidault, Corinne Balleyguier, Victor Aubert, Etienne Bendjebbar, Charles Maussion, Nicolas Loiseau, Benoît Schmauch, Meriem Sefta, Gilles Wainrib, Thomas Clozel, Samy Ammari, Nathalie Lassau
European Journal of Cancer, 2022  
paper
omnitrack OmniTrack: Real-time detection and tracking of objects, text and logos in video
Hannes Fassold, Ridouane Ghermi
IEEE International Symposium on Multimedia (ISM), 2019  
arxiv

Website adapted from Jon Barron.