A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera
This addresses the problem of efficient and accurate human motion analysis from single cameras for applications like surveillance or human-computer interaction, but it is incremental as it builds on existing methods like 2D pose detection and neural architecture search.
The paper tackles joint 3D human pose estimation and action recognition from RGB video by proposing a two-stage deep learning framework, achieving effectiveness on datasets like Human3.6M with low computational costs.
We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important keypoints of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, MSR Action3D and SBU Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.