About Me

Welcome to my website 🙂.

I am a Ph.D. student at the University of Orleans, France. I completed my engineering degree ( Ingénieur d'état ) at the National Institute of Telecommunication and ICT in Oran, Algeria. ( ex. INTTIC, now ENTTIC).

I am interested in deep learning and neural networks, self-supervised learning, and domain adaptation in relation to computer vision. My thesis project aims to model and understand human visual attention mechanisms regarding painting images and cultural heritage.

Published Papers

Kerkouri, Mohamed Amine et al. “Salypath: A Deep-Based Architecture For Visual Attention Prediction.” 2021 IEEE International Conference on Image Processing (ICIP) (2021): 1464-1468. [Arxiv]
Kerkouri, Mohamed Amine et al. “SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images.” January 2022, Electronic Imaging 34(11):168-1-168-7 [Arxiv]
Kerkouri, Mohamed Amine et al. "A simple and efficient deep scanpath prediction." Electronic Imaging 34(11):188-1-188-7,January 2022, DOI: 10.2352/EI.2022.34.11.HVEI-188 [Arxiv]
M. Tliba et al., "SATSal: A Multi-Level Self-Attention Based Architecture for Visual Saliency Prediction," in IEEE Access, vol. 10, pp. 20701-20713, 2022, doi: 10.1109/ACCESS.2022.3152189. [Link]
M. Tliba et al. ,"Self Supervised Scanpath Prediction Framework for Painting Images.", IEEE CVPR-W 2022 [ pdf ]
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, and Alessandro Bruno. 2022. A domain adaptive deep learning solution for scanpath prediction of paintings. In Proceedings of the 19th International Conference on Content-based Multimedia Indexing (CBMI '22). Association for Computing Machinery, New York, NY, USA, 57–63. https://doi.org/10.1145/3549555.3549597 [Arxiv]
M. Tliba et al. "DEEP-BASED QUALITY ASSESSMENT OF MEDICAL IMAGES THROUGH DOMAIN ADAPTATION." International Conference on Image Processing (ICIP) (2022) [Arxiv]