Search Results for author: Kaleab A. Kinfu

Found 3 papers, 2 papers with code

Efficient Vision Transformer for Human Pose Estimation via Patch Selection

no code implementations7 Jun 2023 Kaleab A. Kinfu, Rene Vidal

While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance.

2D Human Pose Estimation 2D Pose Estimation +1

Analysis and Extensions of Adversarial Training for Video Classification

1 code implementation16 Jun 2022 Kaleab A. Kinfu, René Vidal

Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size.

Action Recognition Adversarial Defense +4

Cannot find the paper you are looking for? You can Submit a new open access paper.