no code implementations • 26 Aug 2023 • Khadidja Delloul, Slimane Larabi
In recent years, image captioning and segmentation have emerged as crucial tasks in computer vision, with applications ranging from autonomous driving to content analysis.
1 code implementation • 2 Aug 2023 • Leyla Benhamida, Khadidja Delloul, Slimane Larabi
We test image captioning models on our dataset as well as some skeleton-based human action recognition models in order to extend the range of environment types where a visually disabled person can be, by detecting human actions and textually describing appearances of regions of interest in theatre scenes.
no code implementations • 5 Jul 2023 • Souayah Abdelkader, Mokretar Kraroubi Abderrahmene, Slimane Larabi
People with visual impairments face numerous challenges when interacting with their environment.
no code implementations • 28 Jun 2023 • Leyla Benhamida, Slimane Larabi
The aim of this research is to recognize human actions performed on stage to aid visually impaired and blind individuals.
no code implementations • 20 Jan 2022 • Slimane Larabi
A machine thinking model is proposed in this report based on recent advances of computer vision and the recent results of neuroscience devoted to brain understanding.
no code implementations • 12 Jan 2022 • Leyla Benhamida, Slimane Larabi
The aim of this work is to contribute to the development of a tactile device for visually impaired and blind persons in order to let them to understand actions of the surrounding people and to interact with them.
no code implementations • 27 Dec 2021 • Farah Ibelaiden, Slimane Larabi
This work proposes a new method for place recognition based on the scene architecture.
no code implementations • 9 Aug 2020 • Chayma Zatout, Slimane Larabi
The aim of this work is to provide a semantic scene synthesis from depth image.
no code implementations • 25 Jul 2020 • Slimane Larabi
To do this, features, associated to moving rigid objects in 3D, are extracted in frames and matched.
no code implementations • 21 Jul 2020 • Slimane Larabi, Neil M. Robertson
Given such a reference image, we present a new method based on this expertise to locate contours of a query image in the same way that it is done for the reference (i. e by analogy).