Affective Agents in AR/VR

Overview

This area focuses primarily on generating virtual agents with appropriate emotional expressiveness for a variety of human-agent interactions in social contexts, such as co-habiting and navigating in the same space, conducting conversations, and engaging human audiences.

Publications

Project	Conference/Journal	Year
Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning	ACMMM	2021
Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agent	IEEE VR	2021
Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression	ISMAR	2020
FVA: Modeling Perceived Friendliness of Virtual Agents Using Movement Characteristics	ISMAR	2019
Modeling Data-Driven Dominance Traits for Virtual Characters using Gait Analysis	IEEE TVCG	2019
Pedestrian Dominance Modeling for Socially-Aware Robot Navigation	ICRA	2019
F2FCrowds: Planning Agent Movements to Enable Face-to-Face Interactions	PRESENCE	2017
Generating Virtual Avatars with Personalized Walking Gaits using commodity hardware	ACM Multimedia	2017
PedVR: Simulating Gaze-Based Interactions between a Real User and Virtual Crowds	VRST	2016