R
Rim Slama
Researcher at university of lille
Publications - 13
Citations - 615
Rim Slama is an academic researcher from university of lille. The author has contributed to research in topics: Computer science & Tangent space. The author has an hindex of 5, co-authored 7 publications receiving 508 citations. Previous affiliations of Rim Slama include TELECOM Lille 1 & Centre national de la recherche scientifique.
Papers
More filters
Journal ArticleDOI
3D Face Recognition under Expressions, Occlusions, and Pose Variations
TL;DR: A novel geometric framework for analyzing 3D faces, with the specific goals of comparing, matching, and averaging their shapes, which allows for formal statistical inferences, such as the estimation of missing facial parts using PCA on tangent spaces and computing average shapes.
Journal ArticleDOI
Accurate 3D action recognition using learning on the Grassmann manifold
TL;DR: The intent is to represent skeletal motion in a geometric and efficient way, leading to an accurate action-recognition system, which represents skeletal sequence as point on the Grassmann manifold.
Proceedings ArticleDOI
Grassmannian Representation of Motion Depth for 3D Human Gesture and Action Recognition
TL;DR: This work proposes an original approach to represent geometrical features extracted from depth motion space, which capture both geometric appearance and dynamic of human body simultaneously in this approach, sequence features are modeled temporally as subspaces lying on the Grassmann manifold.
Journal ArticleDOI
Generative Adversarial Networks for Face Generation: A Survey
TL;DR: Facial GANs are reviewed, the progress of architectures are reviewed and the contributions and limits of each are discussed and the encountered problems are exposed and proposed solutions to handle them.
Journal ArticleDOI
3D human motion analysis framework for shape similarity and retrieval
TL;DR: This paper addresses within a new framework the problem of 3D shape representation and shape similarity in human video sequences using extremal human curve descriptor extracted from the body surface and shows the potential of this approach.