Compound Gesture Generation: A Model Based on Ideational Units

Compound Gesture Generation: A Model Based on Ideational Units” by Yuyu Xu, Catherine Pelachaud, and Stacy Marsella. In Proceedings of the 14th International Conference on Intelligent Virtual Agents Best Paper Award, Sep. 2014, pp. 477-491, Springer International Publishing.

Abstract

This work presents a hierarchical framework that generates continuous gesture animation performance for virtual characters. As opposed to approaches that focus more on realizing individual gesture, the focus of this work is on the relation between gestures as part of an overall gesture performance. Following Calbris' work [3], our approach is to structure the performance around ideational units and determine gestural features within and across these ideational units. Furthermore, we use Calbris' work on the relation between form and meaning in gesture to help inform how individual gesture's expressivity is manipulated. Our framework takes in high level communicative function descriptions, generates behavior descriptions and realizes them using our character animation engine. We define the specifications for these different levels of descriptions. Finally, we show the general results as well as experiments illustrating the impacts of the key features.

BibTeX entry:

@inproceedings{yuyuiva14,
   author = {Yuyu Xu and Catherine Pelachaud and Stacy Marsella},
   title = {Compound Gesture Generation: A Model Based on Ideational Units},
   booktitle = {Proceedings of the 14th International Conference on
	Intelligent Virtual Agents {\bf Best Paper Award}},
   pages = {477--491},
   month = sep,
   year = {2014},
   url = {https://stacymarsella.org/publications/pdf/yuyuiva14.pdf},
   organization = {Springer International Publishing}
}

(This webpage was created with bibtex2web.)

Back to Stacy Marsella.