I am PhD student at Le Cnam (in Paris) in deep learning supervised by Nicolas Thome (Sorbonne Université), Nicolas Audebert (Le Cnam) and Clément Rambour (Le Cnam). My thesis is co-financed by Coexya and my industrial supervisor is Xavier Bitot. I use deep learning for Context Based Image Retrieval. I have started my PhD in January 2021 and it will end in January 2024. I have published two projects, ROADMAP at NeurIPS 2021 and HAPPIER at ECCV 2022.

News

• I am going to present our ECCV 2022 paper HAPPIER the 25th of October in Tel Aviv.

Publications

Robust and Decomposable Average Precision for Image Retrieval

Ramzi, E., Thome, N., Rambour, C., Audebert, N., Bitot, X.: Robust and decomposable average precision for image retrieval. Advances in Neural Information Processing Systems 35 (2021).

Hierarchical Average Precision Training for Pertinent Image Retrieval

Ramzi, E., Audebert, N., Thome, N., Rambour, C., Bitot, X.: RHierarchical Average Precision Training for Pertinent Image Retrieval. In: European Conference on Computer Vision. Springer (2022).