most citedConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2023★ 1 cited

ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition

Rachid Reda Dokkar, Faten Chaieb, Hassen Drira +1

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic m…

cs.CV2020

KShapeNet: Riemannian network on Kendall shape space for Skeleton based Action Recognition

Racha Friji, Hassen Drira, Faten Chaieb +2

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 pr…