MPOSE2021: a Dataset for Short-time Pose-based Human Action Recognition

• Main Authors: Mazzia, Vittorio, Angarano, Simone, Salvetti, Francesco, Angelini, Federico, Chiaberge, Marcello
• Format: Dataset
• Language: English
• Published: Zenodo 2021
• Subjects: Deep Learning, Action Recognition, Graph, Classification, 2D Pose, OpenPose, PoseNet; Canada; Hilton; Brighton; laptev
• Online Access: https://dx.doi.org/10.5281/zenodo.5507363; https://zenodo.org/record/5507363

MPOSE2021 MPOSE2021 is a Dataset for short-time pose-based Human Action Recognition (HAR). MPOSE2021 is specifically designed to perform short-time Human Action Recognition, as presented in [12]. MPOSE2021 is developed as an evolution of the MPOSE Dataset [1-3]. It is made by human pose data detecte...