Programmatic Concept Learning for Human Motion Description and Synthesis
Abstract
We introduce Programmatic Motion Concepts, a hierarchical motion representation for human actions that captures both low-level motion and high-level description as motion concepts. This representation enables human motion description, interactive editing, and controlled synthesis of novel video sequences within a single framework. We present an architecture that learns this concept representation from paired video and action sequences in a semi-supervised manner. The compactness of our representation also allows us to present a low-resource training recipe for data-efficient learning. By outperforming established baselines, especially in the small data regime, we demonstrate the efficiency and effectiveness of our framework for multiple applications.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2022
- DOI:
- 10.48550/arXiv.2206.13502
- arXiv:
- arXiv:2206.13502
- Bibcode:
- 2022arXiv220613502K
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Artificial Intelligence;
- Computer Science - Graphics;
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- CVPR 2022. Project page: https://sumith1896.github.io/motion-concepts/