no code implementations • 22 Oct 2023 • Rachid Reda Dokkar, Faten Chaieb, Hassen Drira, Arezki Aberkane
In this research, we propose a novel approach that leverages the strengths of both CNNs and Transformers in an hybrid architecture for performing activity recognition using RGB videos.
no code implementations • 5 May 2021 • Qingkai Zhen, Di Huang, Yunhong Wang, Hassen Drira, Boulbaba Ben Amor, Mohamed Daoudi
In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed.
no code implementations • ICCV 2021 • Rasha Friji, Hassen Drira, Faten Chaieb, Hamza Kchok, Sebastian Kurtek
Deep Learning architectures, albeit successful in mostcomputer vision tasks, were designed for data with an un-derlying Euclidean structure, which is not usually fulfilledsince pre-processed data may lie on a non-linear space. In this paper, we propose a geometry aware deep learn-ing approach using rigid and non rigid transformation opti-mization for skeleton-based action recognition.
no code implementations • 24 Nov 2020 • Racha Friji, Hassen Drira, Faten Chaieb, Sebastian Kurtek, Hamza Kchok
Deep Learning architectures, albeit successful in most computer vision tasks, were designed for data with an underlying Euclidean structure, which is not usually fulfilled since pre-processed data may lie on a non-linear space.
no code implementations • 8 Aug 2019 • Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor
The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors.
no code implementations • CVPR 2018 • Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor
Grounding on the Riemannian geometry of the shape space, an intrinsic sparse coding and dictionary learning formulation is proposed for static skeletal shapes to overcome the inherent non-linearity of the manifold.