Title
Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents**This work has been supported in part by ARO Grants W911NF1910069 and W911NF1910315, and Intel. Code and additional materials available at: https://gamma.umd.edu/t2g
Abstract
We present Text2Gestures, a transformer-based learning method to interactively generate emotive full-body gestures for virtual agents aligned with natural language text inputs. Our method generates emotionally expressive gestures by utilizing the relevant biomechanical features for body expressions, also known as affective features. We also consider the intended task corresponding to the text and ...
Year
DOI
Venue
2021
10.1109/VR50410.2021.00037
2021 IEEE Virtual Reality and 3D User Interfaces (VR)
Keywords
DocType
ISBN
Learning systems,Three-dimensional displays,Correlation,Databases,Natural languages,Pipelines,Graphics processing units
Conference
978-1-6654-1838-6
Citations 
PageRank 
References 
0
0.34
35
Authors
6
Name
Order
Citations
PageRank
Uttaran Bhattacharya1427.10
Nicholas Rewkowski2154.67
Abhishek Banerjee31465.32
Pooja Guhan400.34
Aniket Bera514819.81
Dinesh Manocha69551787.40