Empirical Background



Behavioral differences described in literature are helpful to understand different behavior and are a good guideline for the behavior of virtual characters. For the implementation of computational models, however, they are sometimes too abstract and do not provide enough data to design the differences. A multimodal corpus recorded in different cultural backgrounds that holds information on the observed aspect of behavior is a helpful tool. By analyzing such a corpus, deeper insight into the target behavior is obtained.


Nonverbal Behavior Virtual Character Japanese Participant Gesture Type Topic Shift 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Fachmedien Wiesbaden 2014

Authors and Affiliations

  1. 1.Human Centered MultimediaAugsburg UniversityAugsburgGermany

Personalised recommendations