Temporal Reflection Symmetry of Human Actions: A Riemannian Analysis

Qiao Wang, Rushil Anirudh and Pavan Turaga

Abstract

While spatial symmetry of objects is studied frequently, the problem of measuring temporal symmetry has rarely been explored. In this paper we present a mathematical framework that utilizes a recently developed differential geometric approach to quantify temporal reflection symmetry in movements from video data, in which human movements are modeled as trajectories on Riemannian manifolds. Using the recently proposed transport square-root velocity functions (TSRVF) representation, the amounts of temporal asymmetry in movements are decomposed into a spatial component and a temporal one, each of which is quantified by an asymmetry score.

Session

Workshop: 1st International Workshop on DIFFerential Geometry in Computer Vision for Analysis of Shapes, Images and Trajectories (DIFF-CV)

Files

PDF iconPaper (PDF, 333K)

DOI

10.5244/C.29.DIFFCV.10
https://dx.doi.org/10.5244/C.29.DIFFCV.10

Citation

Qiao Wang, Rushil Anirudh and Pavan Turaga. Temporal Reflection Symmetry of Human Actions: A Riemannian Analysis. In H. Drira, S. Kurtek, and P. Turaga, editors, Proceedings of the 1st International Workshop on DIFFerential Geometry in Computer Vision for Analysis of Shapes, Images and Trajectories (DIFF-CV 2015), pages 10.1-10.8. BMVA Press, September 2015.

Bibtex

@inproceedings{DIFFCV2015_10,
	title={Temporal Reflection Symmetry of Human Actions: A Riemannian Analysis},
	author={Qiao Wang and Rushil Anirudh and Pavan Turaga},
	year={2015},
	month={September},
	pages={10.1-10.8},
	articleno={10},
	numpages={8},
	booktitle={Proceedings of the 1st International Workshop on DIFFerential Geometry in Computer Vision for Analysis of Shapes, Images and Trajectories (DIFF-CV 2015)},
	publisher={BMVA Press},
	editor={H. Drira, S. Kurtek, and P. Turaga},
	doi={10.5244/C.29.DIFFCV.10},
	isbn={1-901725-56-1},
	url={https://dx.doi.org/10.5244/C.29.DIFFCV.10}
}