Researchers: Steve DiPaola, Mahdi Davoodikakhki, Andrey Goncharov, Nilay Ozge Yalcin
The Research
Our open-source toolkit/cognitive research in AI-based 3D Virtual Human (embodied IVA: Intelligence Virtual Agents): a real-time system that can converse with a human by sensing their emotions and conversation (via facial emotion recognition, voice stress, semantics of the speech and words) and respond affectively, emotionally (voice, facial animation, gesture etc.) to a user in front of it via a host of gestural, motion and bio-sensor systems, with several in lab AI systems and give a coherent, personality-based conversational answers via speech, expression and gesture. The system uses Unity and SmartBody (USC) API who we have collaborated with for years. We use cognitive modeling, empathy modelling, NLP and a variety of AI-based modules in our system (see papers).
Please take a look at the videos below to see our affective real-time 3D AI virtual human setup with face emotion recognition, movement recognition and hand gesture recognition:
------ PAPERS: Virtual Humans ------
Expectations vs. Reality; The Impact of Adaptation Gap on Avatars in Social VR Platforms by
Goncharov A; Yalcin ON; DiPaola S – Conference – workshop; ACE; how Artificial Character Embodiment shapes user behaviour in multi-modal interactions. 8 pages
ACM International Conference on Multimodal Interaction (ICMI) (2023)
Expressing Personality Through Non-verbal Behavior in Real-Time Interaction by
Saberi M; DiPaola S; Bernardet U – Journal – Vol 12. 5474. 19 pages
Frontiers in Psychology (2021)
A Dynamic Speech Breathing System for Virtual Characters by
Bernardet U; Kang S; Feng A; DiPaola S; Shapiro A – Conference – pages 43-52
Intelligent Virtual Agents (IVA) (2017)
Simulink Toolbox for Real-time Virtual Character Control by
Bernardet U; Saberi M; DiPaola S – Conference – Lecture Notes in Computer Science. Springer
Intelligent Virtual Agents (IVA) (2016)
m+m; A novel Middleware for Distributed; Movement based Interactive Multimedia Systems by
Bernardet U; Adhia D; ? DiPaola S; ?; Schiphorst T – Conference – pp. 21-30
ACM Movement and Computing (MOCA) (2016)
Exploring Facial Expressions for Human-Computer Interaction; Combining Visual Face Tracking and EMG Data to Control a Flight Simulation Game by
Bayatpour S; Bernardet U; DiPaola S; Kitson A; Riecke B – Conference – Vancouver. 6 pages
International Symposium on Electronic Art (ISEA) (2015)
An Architecture for Personality-Based; Nonverbal Behavior in Affective Virtual Humanoid Character by
Saberi M; Bernardet U; DiPaola S – Journal – Special Issue; Bio Inspired Cognitive Architectures. Vol 41. pp. 204-211
Procedia Computer Science (2014)
Affective Response Patterns as Indicators of Personality in Virtual Characters by
Bernardet U; DiPaola S – Conference – 2 pages. Qu‚bec City
Cognitive Science Society (2014)
Face; Portrait; Mask Using a Parameterized System to Explore Synthetic Face Space by
DiPaola S – Conference – British Computer Society. pp. 296-302. London
Electronic Visualisation and the Arts (EVA) (2010)
Face Modeling and Animation Language for MPEG-4 XMT Framework by
Arya A; DiPaola S – Journal – Vol 9. No 6. pp. 1137-1146
IEEE Transactions on Multimedia (2007)
Face; Portrait; Mask - the Virtuality of the Synthetic Face by
DiPaola S – Conference – Vancouver Art Gallery. 7 pages
Old and New Forms Conference (2004)