1. Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking
2. Skeleton-based action recognition with directed graph neural networks;lei;Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,0
3. Relational inductive biases, deep learning, and graph networks;battaglia;ArXiv Preprint,2018
4. Relation Networks for Object Detection
5. Ntu rgb+ d: A large scale dataset for 3d human activity analysis;amir;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,0