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

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.

Human Activity Recognition