Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
This addresses the problem of inefficient and separate processing in computer vision for applications like surveillance or human-computer interaction, though it is incremental as it builds on existing multi-task and pose/action methods.
The paper tackles the separate handling of human pose estimation and action recognition by proposing a multi-task framework that jointly estimates 2D/3D poses from images and classifies actions from videos, achieving state-of-the-art or comparable results at over 100 frames per second.
Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately. In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences. We show that a single architecture can be used to solve both problems in an efficient way and still achieves state-of-the-art or comparable results at each task while running at more than 100 frames per second. The proposed method benefits from high parameters sharing between the two tasks by unifying still images and video clips processing in a single pipeline, allowing the model to be trained with data from different categories simultaneously and in a seamlessly way. Additionally, we provide important insights for end-to-end training the proposed multi-task model by decoupling key prediction parts, which consistently leads to better accuracy on both tasks. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU RGB+D) demonstrate the effectiveness of our method on the targeted tasks. Our source code and trained weights are publicly available at https://github.com/dluvizon/deephar.