TechRxiv
Vitality Forms paper.pdf (9.47 MB)
Download file

Vitality Forms Analysis and Automatic Recognition

Download (9.47 MB)
preprint
posted on 11.10.2021, 04:26 by Radoslaw NiewiadomskiRadoslaw Niewiadomski, Amrita Suresh, Alessandra Sciutti, Giuseppe DI Cesare
The form of an action, i.e. the way it is performed, conveys important information about the performer’s attitude. In this paper we investigate spatiotemporal characteristics of different gestures performed with specific vitality forms and we study whether it is possible to recognize these aspects of action automatically. As the first step, we created a new dataset of 7 gestures performed with a vitality form (gentle and rude) or without a vitality form (neutral, slow and fast). Thousand repetitions were collected from 2 professional actors. Next, we identified 22 features from the motion capture data. According to the results, vitality forms are not merely characterized by a velocity/acceleration modulation but by a combination of different spatiotemporal properties. We also perform automatic classification of vitality forms with F-score of 87.3%.

Funding

investigating Human Shared PErception with Robots

European Research Council

Find out more...

History

Email Address of Submitting Author

r.niewiadomski@unitn.it

ORCID of Submitting Author

0000-0002-0476-0803

Submitting Author's Institution

University of Trento

Submitting Author's Country

Italy