Temporal Segmentation of Fine-gained Semantic Action: A Motion-Centered Figure Skating Dataset

Authors

  • Shenglan Liu Dalian University of Technology
  • Aibin Zhang Dalian University of Technology
  • Yunheng Li Dalian University of Technology
  • Jian Zhou Dalian University of Technology
  • Li Xu Alibaba Inc.
  • Zhuben Dong Dalian University of Technology
  • Renhao Zhang Dalian University of Technology

Keywords:

Video Understanding & Activity Analysis

Abstract

Temporal Action Segmentation (TAS) has achieved great success in many fields such as exercise rehabilitation, movie editing, etc. Currently, task-driven TAS is a central topic in human action analysis. However, motion-centered TAS, as an important topic, is little researched due to unavailable datasets. In order to explore more models and practical applications of motion-centered TAS, we introduce a Motion-Centered Figure Skating (MCFS) dataset in this paper. Compared with existing temporal action segmentation datasets, the MCFS dataset is fine-grained semantic, specialized and motion-centered. Besides, RGB-based and Skeleton-based features are provided in the MCFS dataset. Experimental results show that existing state-of-the-art methods are difficult to achieve excellent segmentation results (including accuracy, edit and F1 score) in the MCFS dataset. This indicates that MCFS is a challenging dataset for motion-centered TAS. The latest dataset can be downloaded at https://shenglanliu.github.io/mcfs-dataset/.

Downloads

Published

2021-05-18

How to Cite

Liu, S., Zhang, A., Li, Y., Zhou, J., Xu, L., Dong, Z., & Zhang, R. (2021). Temporal Segmentation of Fine-gained Semantic Action: A Motion-Centered Figure Skating Dataset. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2163-2171. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16314

Issue

Section

AAAI Technical Track on Computer Vision II