Publications

@inproceedings{lu_synthetic–real_2024,

title = {Synthetic-to-real adaptation for complex action recognition in surveillance applications},

author = {Shuhong Lu and Zhangyu Jin and Vickram Rajendran and Michal Harari and Andrew Feng and Celso M. De Melo},

editor = {Kimberly E. Manser and Celso De Melo and Raghuveer M. Rao and Christopher L. Howell},

url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/13035/3012393/Synthetic-to-real-adaptation-for-complex-action-recognition-in-surveillance/10.1117/12.3012393.full},

doi = {10.1117/12.3012393},

isbn = {978-1-5106-7388-5 978-1-5106-7389-2},

year  = {2024},

date = {2024-06-01},

urldate = {2024-07-11},

booktitle = {Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II},

pages = {14},

publisher = {SPIE},

address = {National Harbor, United States},

keywords = {DTIC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{greenwald_its_2024,

title = {It's like I'm the AI: Youth Sensemaking About AI through Metacognitive Embodiment},

author = {Eric Greenwald and Ari Krakowski and Timothy Hurt and Kelly Grindstaff and Ning Wang},

url = {https://dl.acm.org/doi/10.1145/3628516.3659395},

doi = {10.1145/3628516.3659395},

isbn = {9798400704420},

year  = {2024},

date = {2024-06-01},

urldate = {2024-06-25},

booktitle = {Proceedings of the 23rd Annual ACM Interaction Design and Children Conference},

pages = {789–793},

publisher = {ACM},

address = {Delft Netherlands},

keywords = {AI, DTIC, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bohy_social-mae_2024,

title = {Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice},

author = {Hugo Bohy and Minh Tran and Kevin El Haddad and Thierry Dutoit and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/10581940/},

doi = {10.1109/FG59268.2024.10581940},

isbn = {9798350394948},

year  = {2024},

date = {2024-05-01},

urldate = {2024-07-18},

booktitle = {2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)},

pages = {1–5},

publisher = {IEEE},

address = {Istanbul, Turkiye},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{jones_designing_2024,

title = {Designing a Proactive Context-Aware AI Chatbot for People's Long-Term Goals},

author = {Brennan Jones and Yan Xu and Qisheng Li and Stefan Scherer},

url = {https://dl.acm.org/doi/10.1145/3613905.3650912},

doi = {10.1145/3613905.3650912},

isbn = {9798400703317},

year  = {2024},

date = {2024-05-01},

urldate = {2024-06-25},

booktitle = {Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},

pages = {1–7},

publisher = {ACM},

address = {Honolulu HI USA},

keywords = {AI, Simulation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mozgai_accelerating_2024,

title = {Accelerating Scoping Reviews: A Case Study in the User-Centered Design of an AI-Enabled Interdisciplinary Research Tool},

author = {Sharon A Mozgai and Cari Kaurloto and Jade G Winn and Andrew Leeds and Sarah Beland and Arman Sookiassian and Arno Hartholt},

url = {https://dl.acm.org/doi/10.1145/3613905.3637110},

doi = {10.1145/3613905.3637110},

isbn = {9798400703317},

year  = {2024},

date = {2024-05-01},

urldate = {2024-06-18},

booktitle = {Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},

pages = {1–8},

publisher = {ACM},

address = {Honolulu HI USA},

keywords = {AI, DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhang_camera_2024,

title = {Camera Calibration using a Single View of a Symmetric Object},

author = {Hui Zhang and Bingran Kuang and Yajie Zhao},

url = {https://ieeexplore.ieee.org/document/10446005/},

doi = {10.1109/ICASSP48485.2024.10446005},

isbn = {9798350344851},

year  = {2024},

date = {2024-04-01},

urldate = {2024-06-25},

booktitle = {ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {2705–2709},

publisher = {IEEE},

address = {Seoul, Korea, Republic of},

keywords = {Graphics, VGL},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{harris_im_2024,

title = {I’m not sure I heard you right, but I think I know what you mean – investigations into the impact of speech recognition errors on response selection for a virtual human.},

author = {Vera Harris and Robert Braggs and David Traum},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://people.ict.usc.edu/~traum/Papers/23-harris-iwsds2024.pdf},

year  = {2024},

date = {2024-03-01},

address = {Sapporo Japan},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{brixey_why_2024,

title = {Why should a dialogue system speak more than one language?},

author = {Jacqueline Brixey and David Traum},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://people.ict.usc.edu/~traum/Papers/24-Why%20should%20a%20dialogue%20system%20speak%20more%20than%20one%20language.pdf},

year  = {2024},

date = {2024-03-01},

address = {Sapporo Japan},

keywords = {Natural Language},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gordon_combining_2024,

title = {Combining the Predictions of Out-of-Domain Classifiers Using Etcetera Abduction},

author = {Andrew S. Gordon and Andrew Feng},

url = {https://ieeexplore.ieee.org/document/10480194/},

doi = {10.1109/CISS59072.2024.10480194},

isbn = {9798350369298},

year  = {2024},

date = {2024-03-01},

urldate = {2024-04-16},

booktitle = {2024 58th Annual Conference on Information Sciences and Systems (CISS)},

pages = {1–6},

publisher = {IEEE},

address = {Princeton, NJ, USA},

keywords = {DTIC, Narrative, The Narrative Group, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ustun_assessing_2024,

title = {Assessing Routing Decisions of Search and Rescue Teams in Service of an Artificial Social Intelligence Agent:},

author = {Volkan Ustun and Ronit Jorvekar and Nikolos Gurney and David Pynadath and Yunzhe Wang},

url = {https://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0012388100003636},

doi = {10.5220/0012388100003636},

isbn = {978-989-758-680-4},

year  = {2024},

date = {2024-02-01},

urldate = {2024-03-19},

booktitle = {Proceedings of the 16th International Conference on Agents and Artificial Intelligence},

pages = {313–320},

publisher = {SCITEPRESS - Science and Technology Publications},

address = {Rome, Italy},

keywords = {AI, Cognitive Architecture, Social Simulation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{awada_investigating_2024,

title = {Investigating the Interplay between Indoor Environmental Quality and Workers’ Health and Productivity: Preliminary Results},

author = {Mohamad Awada and Mirmahdi Seyedrezaei and Burcin Becerik-Gerber and Gale Lucas},

url = {https://ascelibrary.org/doi/10.1061/9780784485248.074},

doi = {10.1061/9780784485248.074},

isbn = {978-0-7844-8524-8},

year  = {2024},

date = {2024-01-01},

urldate = {2024-04-16},

booktitle = {Computing in Civil Engineering 2023},

pages = {614–622},

publisher = {American Society of Civil Engineers},

address = {Corvallis, Oregon},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu_development_2024,

title = {Development of a VR Training Platform for Active Shooter Incident Preparedness in Healthcare Environments via a Stakeholder-Engaged Process},

author = {Ruying Liu and Burçin Becerik-Gerber and Gale M. Lucas and Kelly Busta},

url = {https://ascelibrary.org/doi/10.1061/9780784485231.006},

doi = {10.1061/9780784485231.006},

isbn = {978-0-7844-8523-1},

year  = {2024},

date = {2024-01-01},

urldate = {2024-04-16},

booktitle = {Computing in Civil Engineering 2023},

pages = {45–53},

publisher = {American Society of Civil Engineers},

address = {Corvallis, Oregon},

keywords = {Virtual Humans, VR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rodrigues_virtual_2024,

title = {Virtual Environment for Studying the Effects of Operational and Environmental Sounds on Teleoperated Demolition},

author = {Patrick B. Rodrigues and Burcin Becerik-Gerber and Lucio Soibelman and Gale M. Lucas and Shawn C. Roll},

url = {https://ascelibrary.org/doi/10.1061/9780784485231.007},

doi = {10.1061/9780784485231.007},

isbn = {978-0-7844-8523-1},

year  = {2024},

date = {2024-01-01},

urldate = {2024-04-16},

booktitle = {Computing in Civil Engineering 2023},

pages = {54–61},

publisher = {American Society of Civil Engineers},

address = {Corvallis, Oregon},

keywords = {DTIC, Virtual Humans, VR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hartholt_multidisciplinary_2024,

title = {Multidisciplinary Research & Development of Multi-Agents and Virtual Humans Leveraging Integrated Middleware Platforms},

author = {Arno Hartholt and Andrew Leeds and Ed Fast and Edwin Sookiassian and Kevin Kim and Sarah Beland and Pranav Kulkarni and Sharon Mozgai},

url = {https://openaccess.cms-conferences.org/publications/book/978-1-958651-95-7/article/978-1-958651-95-7_33},

doi = {10.54941/ahfe1004497},

year  = {2024},

date = {2024-01-01},

urldate = {2024-04-16},

abstract = {The current pace of technological advancements has led to an ever-increasing availability of technologies to investigate and help address the challenges that contemporary society faces today. However, while this trend increases the potential for creating more relevant, effective, and efficient solutions, it also inherently increases the complexity of realizing that potential. Our work aims to manage this complexity through the creation and dissemination of integrated middleware platforms that enable researchers and developers to rapidly prototype novel solutions within the areas of modelling & simulation, virtual humans, and virtual worlds. In this paper, we discuss two related platforms: the Rapid Integration & Development Environment (RIDE) and the Virtual Human Toolkit (VHToolkit). Specifically, we explore two use cases: 1) the development of an authoring tool aimed at domain experts to rapidly create low-echelon military training scenarios, and 2) the development of a virtual human led mHealth wellness and suicide prevention app for veterans.},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu_assessing_2024,

title = {Assessing Workers’ Operational Postures via Egocentric Camera Mapping},

author = {Ziming Liu and Christine Wun Ki Suen and Zhengbo Zou and Meida Chen and Yangming Shi},

url = {https://ascelibrary.org/doi/10.1061/9780784485224.003},

doi = {10.1061/9780784485224.003},

isbn = {978-0-7844-8522-4},

year  = {2024},

date = {2024-01-01},

urldate = {2024-03-19},

booktitle = {Computing in Civil Engineering 2023},

pages = {17–24},

publisher = {American Society of Civil Engineers},

address = {Corvallis, Oregon},

keywords = {Narrative, STG},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhou_investigating_2023,

title = {Investigating the Generalizability of Physiological Characteristics of Anxiety},

author = {Emily Zhou and Mohammad Soleymani and Maja J. Matarić},

url = {https://ieeexplore.ieee.org/document/10385292/},

doi = {10.1109/BIBM58861.2023.10385292},

isbn = {9798350337488},

year  = {2023},

date = {2023-12-01},

urldate = {2024-04-16},

booktitle = {2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},

pages = {4848–4855},

publisher = {IEEE},

address = {Istanbul, Turkiye},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chemburkar_discrete_2023,

title = {Discrete Diffusion for Co-Speech Gesture Synthesis},

author = {Ankur Chemburkar and Shuhong Lu and Andrew Feng},

url = {https://dl.acm.org/doi/10.1145/3610661.3616556},

doi = {10.1145/3610661.3616556},

isbn = {9798400703218},

year  = {2023},

date = {2023-10-01},

urldate = {2024-07-09},

booktitle = {International Cconference on Multimodal Interaction},

pages = {186–192},

publisher = {ACM},

address = {Paris France},

keywords = {DTIC, Natural Language},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nasihati_gilani_multimodal_2023,

title = {Multimodal Prediction of User's Performance in High-Stress Dialogue Interactions},

author = {Setareh Nasihati Gilani and Kimberly Pollard and David Traum},

url = {https://dl.acm.org/doi/10.1145/3610661.3617166},

doi = {10.1145/3610661.3617166},

isbn = {9798400703218},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {71–75},

publisher = {ACM},

address = {Paris France},

keywords = {DTIC, Natural Language, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lin_toward_2023,

title = {Toward a Better Understanding of the Emotional Dynamics of Negotiation with Large Language Models},

author = {Eleanor Lin and James Hale and Jonathan Gratch},

url = {https://dl.acm.org/doi/10.1145/3565287.3617637},

doi = {10.1145/3565287.3617637},

isbn = {978-1-4503-9926-5},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {Proceedings of the Twenty-fourth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing},

pages = {545–550},

publisher = {ACM},

address = {Washington DC USA},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ahmed_asar_2023,

title = {ASAR Dataset and Computational Model for Affective State Recognition During ARAT Assessment for Upper Extremity Stroke Survivors},

author = {Tamim Ahmed and Thanassis Rikakis and Aisling Kelliher and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3610661.3617154},

doi = {10.1145/3610661.3617154},

isbn = {9798400703218},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {11–15},

publisher = {ACM},

address = {Paris France},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{andrist_platform_2023,

title = {Platform for Situated Intelligence and OpenSense: A Tutorial on Building Multimodal Interactive Applications for Research},

author = {Sean Andrist and Dan Bohus and Zongjian Li and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3610661.3617603},

doi = {10.1145/3610661.3617603},

isbn = {9798400703218},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {International Cconference on Multimodal Interaction},

pages = {105–106},

publisher = {ACM},

address = {Paris France},

keywords = {AI, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_multimodal_2023,

title = {Multimodal Analysis and Assessment of Therapist Empathy in Motivational Interviews},

author = {Trang Tran and Yufeng Yin and Leili Tavabi and Joannalyn Delacruz and Brian Borsari and Joshua D Woolley and Stefan Scherer and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3577190.3614105},

doi = {10.1145/3577190.3614105},

isbn = {9798400700552},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

booktitle = {INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION},

pages = {406–415},

publisher = {ACM},

address = {Paris France},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lei_sources_2023,

title = {Sources of Facial Expression Synchrony},

author = {Su Lei and Jonathan Gratch},

url = {https://ieeexplore.ieee.org/document/10388107/},

doi = {10.1109/ACII59096.2023.10388107},

isbn = {9798350327434},

year  = {2023},

date = {2023-09-01},

urldate = {2024-07-16},

booktitle = {2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–8},

publisher = {IEEE},

address = {Cambridge, MA, USA},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yang_context_2023-1,

title = {Context Unlocks Emotions: Text-based Emotion Classification Dataset Auditing with Large Language Models},

author = {Daniel Yang and Aditya Kommineni and Mohammad Alshehri and Nilamadhab Mohanty and Vedant Modi and Jonathan Gratch and Shrikanth Narayanan},

url = {https://ieeexplore.ieee.org/document/10388131/},

doi = {10.1109/ACII59096.2023.10388131},

isbn = {9798350327434},

year  = {2023},

date = {2023-09-01},

urldate = {2024-08-13},

booktitle = {2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–8},

publisher = {IEEE},

address = {Cambridge, MA, USA},

keywords = {Emotions},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hoegen_how_2023,

title = {How Expression and Context Determine Second-person Judgments of Emotion},

author = {Jessie Hoegen and Gale Lucas and Danielle Shore and Brian Parkinson and Jonathan Gratch},

url = {https://ieeexplore.ieee.org/document/10388189/},

doi = {10.1109/ACII59096.2023.10388189},

isbn = {9798350327434},

year  = {2023},

date = {2023-09-01},

urldate = {2024-07-09},

booktitle = {2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–7},

publisher = {IEEE},

address = {Cambridge, MA, USA},

keywords = {DTIC, Emotion},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gainer_divis_2023,

title = {DIVIS: Digital Interactive Victim Intake Simulator},

author = {Alesia Gainer and Allison Aptaker and Ron Artstein and David Cobbins and Mark Core and Carla Gordon and Anton Leuski and Zongjian Li and Chirag Merchant and David Nelson and Mohammad Soleymani and David Traum},

url = {https://dl.acm.org/doi/10.1145/3570945.3607328},

doi = {10.1145/3570945.3607328},

isbn = {978-1-4503-9994-4},

year  = {2023},

date = {2023-09-01},

urldate = {2024-02-20},

booktitle = {Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents},

pages = {1–2},

publisher = {ACM},

address = {Würzburg Germany},

keywords = {DTIC, MxR, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_personalized_2023,

title = {Personalized Adaptation with Pre-trained Speech Encoders for Continuous Emotion Recognition},

author = {Minh Tran and Yufeng Yin and Mohammad Soleymani},

url = {https://www.isca-speech.org/archive/interspeech_2023/tran23c_interspeech.html},

doi = {10.21437/Interspeech.2023-2170},

year  = {2023},

date = {2023-08-01},

urldate = {2023-08-23},

booktitle = {INTERSPEECH 2023},

pages = {636–640},

publisher = {ISCA},

keywords = {DTIC, Emotions, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mozgai_human-centered_2023,

title = {Human-Centered Design for a Virtual Human led mHealth Intervention for Suicide Prevention},

author = {Sharon Mozgai and Albert Rizzo and Arno Hartholt},

url = {https://openaccess.cms-conferences.org/publications/book/978-1-958651-88-9/article/978-1-958651-88-9_11},

doi = {10.54941/ahfe1004118},

year  = {2023},

date = {2023-07-01},

urldate = {2024-07-11},

abstract = {Addressing the significant mental and physical healthcare needs of 

 Veterans requires innovative strategies to enhance access to evidence-based 

 care. The integration of Virtual Human (VH) agents into Mobile Health 

 (mHealth) applications presents a promising opportunity to overcome barriers 

 associated with suicide prevention and connect with Veterans. The Battle 

 Buddy (BB) project was conceived as a mobile wellness and suicide prevention 

 application, empowering Veterans with an always-available resource 

 concierged by an engaging and supportive conversational VH agent. 

 Human-centered design is essential in the development of all interactions 

 focused on the persuasive strategies of (1) personalization, (2) 

 self-monitoring, (3) tunneling, (4) suggestion, and (5) expertise. Veterans 

 can interact with the BB VH during daily check-ins, learn about mental 

 health and wellness strategies, participate in interactive activities, 

 increase self-awareness of their current status, and build and work safety 

 plans in times of suicidal crisis. BB is designed to provide the Veteran 

 with easy access to a suicide prevention ecosystem in which a wealth of 

 evidenced-based interventions will be delivered in a non-stigmatizing 

 fashion by a computer-based dialogue system with virtual embodiment, 

 utilizing various multi-modal language cues such as text, speech, animated 

 facial expressions, and gestures to interact with users. This paper explores 

 our human-centered design process for the BB feature set to target the 

 negative effects of social isolation and loneliness, conditions that 

 challenge Veteran healthcare and suicide prevention.},

keywords = {MedVR},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nye_mentorstudio_2023,

title = {MentorStudio: Amplifying diverse voices through rapid, self-authorable virtual mentors},

author = {Benjamin D. Nye and Yuko Okado and Aaron Shiel and Kayla Carr and Milton Rosenberg and Enora Rice and Luke Ostrander and Megan Ju and Cassandra Gutierrez and Dilan Ramirez and Daniel Auerbach and Angelica Aguirre and William Swartout},

url = {https://zenodo.org/record/8226275},

doi = {10.5281/ZENODO.8226275},

year  = {2023},

date = {2023-07-01},

urldate = {2024-01-11},

abstract = {Mentoring promotes underserved students' STEM persistence but it is difficult to scale up. Virtual agents can amplify mentors' experiences to larger audiences, which is particularly important for mentors from under-represented backgrounds and for underserved students with less access to mentors. This paper introduces MentorStudio, an online platform that allows real-life mentors to self-record and publish video-based conversational virtual agents. MentorStudio's goals are to increase speed, scheduling flexibility, and autonomy in creating intelligent virtual mentors. MentorStudio platform components are introduced, along with initial feedback regarding usability and acceptance collected from 20 STEM mentors who recorded virtual mentors. Overall, the MentorStudio platform has good ease-of-use and acceptance among mentors and offers a platform capable of recording large number of mentors to expand their reach to an unlimited number of students.},

note = {Publisher: Zenodo},

keywords = {DTIC, Learning Sciences, UARC, Virtual Agents},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nye_generative_2023,

title = {Generative Large Language Models for Dialog-Based Tutoring: An Early Consideration of Opportunities and Concerns},

author = {Benjamin D Nye and Dillon Mee and Mark G Core},

url = {https://ceur-ws.org/Vol-3487/paper4.pdf},

year  = {2023},

date = {2023-07-01},

abstract = {After many years of relatively limited capabilities for generative language models, recent large language models (LLM’s) have demonstrated qualitatively better capabilities for understanding, synthesis, and inference on text. Due to the prominence of ChatGPT’s chat system, both the media and many educational developers have suggested using generative AI to directly tutor students. However, despite surface-level similarity between ChatGPT interactions and tutoring dialogs, generative AI has other strengths which may be substantially more relevant for intelligent tutoring (e.g., detecting misconceptions, improved language translation, content generation) and weaknesses that make it problematic for on-the-fly tutoring (e.g., hallucinations, lack of pedagogical training data). In this paper, we discuss how we are approaching generative LLM’s for tutoring dialogs, for problems such as multi- concept short answer grading and semi-supervised interactive content generation. This work shows interesting opportunities for prompt engineering approaches for short-answer classification, despite sometimes quirky behavior. The time savings for high-quality content generation for tutoring is not yet clear and further research is needed. The paper concludes with a consideration of longer-term equity and access in a world where essential capabilities require low-latency real-time connections to large, pay-peruse models. Risks and mitigating technologies for this kind of “AI digital divide” are discussed, including optimized / edge-computing LLM’s and using generative AI models as simulated students to train specialized tutoring models.},

keywords = {DTIC, Learning Sciences, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hartholt_creating_2023,

title = {Creating Virtual Worlds with the Virtual Human Toolkit and the Rapid Integration & Development Environment},

author = {Arno Hartholt and Sharon Mozgai},

url = {https://openaccess.cms-conferences.org/publications/book/978-1-958651-45-2/article/978-1-958651-45-2_41},

doi = {10.54941/ahfe1002856},

isbn = {978-1-958651-45-2},

year  = {2023},

date = {2023-07-01},

urldate = {2023-03-31},

booktitle = {Intelligent Human Systems Integration (IHSI 2023): Integrating People and Intelligent Systems},

volume = {69},

publisher = {AHFE Open Acces},

abstract = {The research and development of virtual humans, and the virtual worlds they inhabit, is inherently complex, requiring interdisciplinary approaches that combine social sciences, computer science, design, art, production, and domain expertise. Our previous work in managing this complexity has resulted in the release of the Virtual Human Toolkit (VHToolkit), aimed at lowering the burden of creating embodied conversational agents. In our current efforts, we are integrating the VHToolkit with the Rapid Integration & Development Environment (RIDE), a rapid prototyping modeling and simulation middleware platform that leverages real-time game engines. This integration results in the ability to mix and match commercial AI services from AWS, Azure, and Google, as well as leverage novel 3D geospatial terrain creation pipelines. Combined with dedicated authoring tools that have been developed through human-centered design processes, the platform enables researchers, developers, and domain experts to rapidly create digital worlds with virtual humans for both military and civilian contexts. Our approach is highly interdisciplinary, including academia, government, and industry collaborators. The demonstration shows a user interacting with an embodied conversational agent embedded within real-world captured and virtualized terrain. Further research and development features of the platform are shown, including scripted agent behaviors, networked team play, and machine learning interfaces.},

note = {ISSN: 27710718 

Issue: 69},

keywords = {DTIC, UARC, VHTL, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_speech_2023,

title = {A Speech Representation Anonymization Framework via Selective Noise Perturbation},

author = {Minh Tran and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/document/10095173/},

doi = {10.1109/ICASSP49357.2023.10095173},

isbn = {978-1-72816-327-7},

year  = {2023},

date = {2023-06-01},

urldate = {2023-08-23},

booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {1–5},

publisher = {IEEE},

address = {Rhodes Island, Greece},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pynadath_effectiveness_2023,

title = {Effectiveness of Teamwork-Level Interventions through Decision-Theoretic Reasoning in a Minecraft Search-and-Rescue Task},

author = {David V Pynadath and Nikolos Gurney and Sarah Kenny and Rajay Kumar and Stacy C. Marsella and Haley Matuszak and Hala Mostafa and Volkan Ustun and Peggy Wu and Pedro Sequeira},

url = {https://dl.acm.org/doi/10.5555/3545946.3598925},

year  = {2023},

date = {2023-05-01},

booktitle = {AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems},

pages = {Pages 2334–2336},

abstract = {Autonomous agents offer the promise of improved human teamwork through automated assessment and assistance during task performance [15, 16, 18]. Studies of human teamwork have identified various processes that underlie joint task performance, while abstracting away the specifics of the task [7, 11, 13, 17].We present here an agent that focuses exclusively on teamwork-level variables in deciding what interventions to use in assisting a human team. Our agent does not directly observe or model the environment or the people in it, but instead relies on input from analytic components (ACs) (developed by other research teams) that process environmental information and output only teamwork-relevant measures. Our agent models these teamwork variables and updates its beliefs over them using a Bayesian Theory of Mind [1], applying Partially Observable Markov Decision Processes (POMDPs) [9] in a recursive manner to assess the state of the team it is currently observing and to choose interventions to best assist them.},

keywords = {DTIC, Social Simulation, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gordon_searching_2023,

title = {Searching for the Most Probable Combination of Class Labels Using Etcetera Abduction},

author = {Andrew S. Gordon and Andrew Feng},

url = {https://ieeexplore.ieee.org/document/10089729/},

doi = {10.1109/CISS56502.2023.10089729},

isbn = {978-1-66545-181-9},

year  = {2023},

date = {2023-03-01},

urldate = {2023-08-07},

booktitle = {2023 57th Annual Conference on Information Sciences and Systems (CISS)},

pages = {1–6},

publisher = {IEEE},

address = {Baltimore, MD, USA},

keywords = {DTIC, Narrative, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_considerations_2023,

title = {Considerations for Child Speech Synthesis for Dialogue Systems},

author = {Kallirroi Georgila},

url = {https://kgeorgila.github.io/publications/georgila_aiaic23.pdf},

year  = {2023},

date = {2023-03-01},

address = {Los Angeles, CA},

abstract = {We present a number of important issues for consideration with regard to child speech synthesis for dialogue systems. We specifically discuss challenges in building child synthetic voices compared to adult synthetic voices, synthesizing expressive conversational speech, and evaluating speech synthesis quality.},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chemburkar_moddm_2023,

title = {MoDDM: Text-to-Motion Synthesis using Discrete Diffusion Model},

author = {Ankur Chemburkar and Shuhong Lu and Andrew Feng},

url = {chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://papers.bmvc2023.org/0624.pdf},

year  = {2023},

date = {2023-01-01},

abstract = {We present the motion discrete diffusion model (MoDDM) for synthesizing human motion from text descriptions that addresses challenges in cross-modal mapping and motion diversity. The previous methods that utilized variational autoencoder (VAE) to learn the latent distributions for text-to-motion synthesis tend to produce motions with less diversity and fidelity. While the diffusion models show promising results by generating high quality motions, they require higher computational costs and may produce motions less aligned with the input text. The proposed method combines the discrete latent space and diffusion models to learn an expressive conditional probabilistic mapping for motion synthesis. Our method utilizes vector quantization variational autoencoder (VQ-VAE) to learn discrete motion tokens and then applies discrete denoising diffusion probabilistic models (D3PM) to learn the conditional probability distributions for the motion tokens. The discrete classifier-free guidance is further utilized in the training process with proper guidance scale for aligning the motions and the corresponding text descriptions. By learning the denoising model in the discrete latent space, the method produces high quality motion results while greatly reducing computational costs compared to training the diffusion models on raw motion sequences. The evaluation results show that the proposed approach outperforms previous methods in both motion quality and text-to-motion matching accuracy.},

keywords = {VGL},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mozgai_toward_2023,

title = {Toward a Scoping Review of Social Intelligence in Virtual Humans},

author = {Sharon Mozgai and Sarah Beland and Andrew Leeds and Jade G. Winn and Cari Kaurloto and Dirk Heylen and Arno Hartholt},

url = {https://ieeexplore.ieee.org/abstract/document/10042532},

doi = {10.1109/FG57933.2023.10042532},

year  = {2023},

date = {2023-01-01},

booktitle = {2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)},

pages = {1–6},

abstract = {As the demand for socially intelligent Virtual Humans (VHs) increases, so follows the demand for effective and efficient cross-discipline collaboration that is required to bring these VHs “to life”. One avenue for increasing cross-discipline fluency is the aggregation and organization of seemingly disparate areas of research and development (e.g., graphics and emotion models) that are essential to the field of VH research. Our initial investigation (1) identifies and catalogues research streams concentrated in three multidisciplinary VH topic clusters within the domain of social intelligence, Emotion, Social Behavior, and The Face, (2) brings to the forefront key themes and prolific authors within each topic cluster, and (3) provides evidence that a full scoping review is warranted to further map the field, aggregate research findings, and identify gaps in the research. To enable collaboration, we provide full access to the refined VH cluster datasets, key word and author word clouds, as well as interactive evidence maps.},

keywords = {DTIC, UARC, VHTL, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{feng_tool_2022,

title = {A Tool for Extracting 3D Avatar-Ready Gesture Animations from Monocular Videos},

author = {Andrew Feng and Samuel Shin and Youngwoo Yoon},

url = {https://dl.acm.org/doi/10.1145/3561975.3562953},

doi = {10.1145/3561975.3562953},

isbn = {978-1-4503-9888-6},

year  = {2022},

date = {2022-11-01},

urldate = {2023-08-04},

booktitle = {Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games},

pages = {1–7},

publisher = {ACM},

address = {Guanajuato Mexico},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lu_deepmotion_2022,

title = {The DeepMotion entry to the GENEA Challenge 2022},

author = {Shuhong Lu and Andrew Feng},

url = {https://dl.acm.org/doi/10.1145/3536221.3558059},

doi = {10.1145/3536221.3558059},

isbn = {978-1-4503-9390-4},

year  = {2022},

date = {2022-11-01},

urldate = {2023-08-24},

booktitle = {INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION},

pages = {790–796},

publisher = {ACM},

address = {Bengaluru India},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yin_x-norm_2022,

title = {X-Norm: Exchanging Normalization Parameters for Bimodal Fusion},

author = {Yufeng Yin and Jiashu Xu and Tianxin Zu and Mohammad Soleymani},

url = {https://dl.acm.org/doi/10.1145/3536221.3556581},

doi = {10.1145/3536221.3556581},

isbn = {978-1-4503-9390-4},

year  = {2022},

date = {2022-11-01},

urldate = {2023-08-24},

booktitle = {INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION},

pages = {605–614},

publisher = {ACM},

address = {Bengaluru India},

keywords = {DTIC, Emotions, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhang_speech_2022,

title = {Speech Behavioral Markers Align on Symptom Factors in Psychological Distress},

author = {Larry Zhang and Jacek Kolacz and Albert Rizzo and Stefan Scherer and Mohammad Soleymani},

url = {https://ieeexplore.ieee.org/abstract/document/9953849},

doi = {10.1109/ACII55700.2022.9953849},

year  = {2022},

date = {2022-10-01},

booktitle = {2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII)},

pages = {1–8},

abstract = {Automatic detection of psychological disorders has gained significant attention in recent years due to the rise in their prevalence. However, the majority of studies have overlooked the complexity of disorders in favor of a “present/not present” dichotomy in representing disorders. Recent psychological research challenges favors transdiagnostic approaches, moving beyond general disorder classifications to symptom level analysis, as symptoms are often not exclusive to individual disorder classes. In our study, we investigated the link between speech signals and psychological distress symptoms in a corpus of 333 screening interviews from the Distress Analysis Interview Corpus (DAIC). Given the semi-structured organization of interviews, we aggregated speech utterances from responses to shared questions across interviews. We employed deterministic sample selection in classification to rank salient questions for eliciting symptom-specific behaviors in order to predict symptom presence. Some questions include “Do you find therapy helpful?” and “When was the last time you felt happy?”. The prediction results align closely to the factor structure of psychological distress symptoms, linking speech behaviors primarily to somatic and affective alterations in both depression and PTSD. This lends support for the transdiagnostic validity of speech markers for detecting such symptoms. Surprisingly, we did not find a strong link between speech markers and cognitive or psychomotor alterations. This is surprising, given the complexity of motor and cognitive actions required in speech production. The results of our analysis highlight the importance of aligning affective computing research with psychological research to investigate the use of automatic behavioral sensing to assess psychiatric risk.},

note = {ISSN: 2156-8111},

keywords = {DTIC, MedVR, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{brixey_towards_2022,

title = {Towards an Automatic Speech Recognizer for the Choctaw language},

author = {Jacqueline Brixey and David Traum},

url = {https://www.isca-speech.org/archive/s4sg_2022/brixey22_s4sg.html},

doi = {10.21437/S4SG.2022-2},

year  = {2022},

date = {2022-09-01},

urldate = {2023-03-31},

booktitle = {1st Workshop on Speech for Social Good (S4SG)},

pages = {6–9},

publisher = {ISCA},

keywords = {Natural Language, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hale_preference_2022,

title = {Preference interdependencies in a multi-issue salary negotiation},

author = {James Hale and Peter Kim and Jonathan Gratch},

url = {https://doi.org/10.1145/3514197.3549681},

doi = {10.1145/3514197.3549681},

isbn = {978-1-4503-9248-8},

year  = {2022},

date = {2022-09-01},

urldate = {2022-09-27},

booktitle = {Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents},

pages = {1–8},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {IVA '22},

abstract = {Negotiation is an important potential application domain for intelligent virtual agents but, unlike research on agent-agent negotiations, agents that negotiate with people often adopt unrealistic simplifying assumptions. These assumptions not only limit the generality of these agents, but call into question scientific findings about how people negotiate with agents. Here we relax two common assumptions: the use of assigned rather than elicited user preferences, and the use of linear utility functions. Using a simulated salary negotiation, we find that relaxing these assumptions helps reveal interesting individual differences in how people negotiate their salary and allows algorithms to find better win-win solutions.},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hale_negotiation_2022,

title = {Negotiation game to introduce non-linear utility},

author = {James Hale and Harsh Jalan and Nidhi Saini and Shao Ling Tan and Junhyuck Woo and Jonathan Gratch},

url = {https://doi.org/10.1145/3514197.3549678},

doi = {10.1145/3514197.3549678},

isbn = {978-1-4503-9248-8},

year  = {2022},

date = {2022-09-01},

urldate = {2022-09-27},

booktitle = {Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents},

pages = {1–3},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {IVA '22},

abstract = {Much prior work in automated negotiation makes the simplifying assumption of linear utility functions. As such, we propose a framework for multilateral repeated negotiations in a complex game setting—to introduce non-linearities—where negotiators can choose with whom they negotiate in subsequent games. This game setting not only creates non-linear utility functions, but also motivates the negotiation.},

keywords = {DTIC, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lee_examining_2022,

title = {Examining the impact of emotion and agency on negotiator behavior},

author = {Eugene Lee and Zachary McNulty and Alex Gentle and Prerak Tusharkumar Pradhan and Jonathan Gratch},

url = {https://doi.org/10.1145/3514197.3549673},

doi = {10.1145/3514197.3549673},

isbn = {978-1-4503-9248-8},

year  = {2022},

date = {2022-09-01},

urldate = {2022-09-27},

booktitle = {Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents},

pages = {1–3},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {IVA '22},

abstract = {Virtual human expressions can shape user behavior [1, 2, 3], yet in negotiation, findings have been underwhelming. For example, human negotiators can use anger to claim value (i.e., extract concessions) [4], but anger has no effect when exhibited by a virtual human [5]. Other psychological work suggests that emotions can create value (e.g., happy negotiators can better discover tradeoffs across issues that "grow the pie"), but little research has examined how virtual human expressions shape value creation. Here we present an agent architecture and pilot study that examines differences between how the emotional expressions of human and virtual-human opponents shape value claiming and value creation. We replicate the finding that virtual human anger fails to influence value claiming but discover counter-intuitive findings on value creation. We argue these findings highlight the potential for intelligent virtual humans to yield insight into human psychology.},

keywords = {DTIC, Emotions, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hartholt_re-architecting_2022,

title = {Re-architecting the virtual human toolkit: towards an interoperable platform for embodied conversational agent research and development},

author = {Arno Hartholt and Ed Fast and Zongjian Li and Kevin Kim and Andrew Leeds and Sharon Mozgai},

url = {https://dl.acm.org/doi/10.1145/3514197.3549671},

doi = {10.1145/3514197.3549671},

isbn = {978-1-4503-9248-8},

year  = {2022},

date = {2022-09-01},

urldate = {2022-09-15},

booktitle = {Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents},

pages = {1–8},

publisher = {ACM},

address = {Faro Portugal},

keywords = {DTIC, UARC, VHTL, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{georgila_comparing_2022,

title = {Comparing Regression Methods for Dialogue System Evaluation on a Richly Annotated Corpus},

author = {Kallirroi Georgila},

url = {http://semdial.org/anthology/papers/Z/Z22/Z22-3011/},

year  = {2022},

date = {2022-08-01},

urldate = {2023-03-31},

booktitle = {Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers},

abstract = {Wecompare various state-of-the-art regression methods for predicting user ratings of their interaction with a dialogue system using a richly annotated corpus. We vary the size of the training data and, in particular for kernel-based methods, we vary the type of kernel used. Furthermore, we experiment with various domainindependent features, including feature combinations that do not rely on complex annotations. We present detailed results in terms of root mean square error, and Pearson’s r and Spearman’s ρ correlations. Our results show that in many cases Gaussian Process Regression leads to modest but statistically significant gains compared to Support Vector Regression (a strong baseline), and that the type of kernel used matters. The gains are even larger when compared to linear regression. The larger the training data set the higher the gains but for some cases more data may result in over-fitting. Finally, some feature combinations work better than others but overall the best results are obtained when all features are used.},

keywords = {Natural Language, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pynadath_explainable_2022,

title = {Explainable Reinforcement Learning in Human-Robot Teams: The Impact of Decision-Tree Explanations on Transparency},

author = {David V. Pynadath and Nikolos Gurney and Ning Wang},

doi = {10.1109/RO-MAN53752.2022.9900608},

year  = {2022},

date = {2022-08-01},

booktitle = {2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},

pages = {749–756},

abstract = {Understanding the decisions of AI-driven systems and the rationale behind such decisions is key to the success of the human-robot team. However, the complexity and the "black-box" nature of many AI algorithms create a barrier for establishing such understanding within their human counterparts. Reinforcement Learning (RL), a machine-learning algorithm based on the simple idea of action-reward mappings, has a rich quantitative representation and a complex iterative reasoning process that present a significant obstacle to human understanding of, for example, how value functions are constructed, how the algorithms update the value functions, and how such updates impact the action/policy chosen by the robot. In this paper, we discuss our work to address this challenge by developing a decision-tree based explainable model for RL to make a robot’s decision-making process more transparent. Set in a human-robot virtual teaming testbed, we conducted a study to assess the impact of the explanations, generated using decision trees, on building transparency, calibrating trust, and improving the overall human-robot team’s performance. We discuss the design of the explainable model and the positive impact of the explanations on outcome measures.},

note = {ISSN: 1944-9437},

keywords = {Social Simulation, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kuang_densegap_2022,

title = {DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points},

author = {Zhengfei Kuang and Jiaman Li and Mingming He and Tong Wang and Yajie Zhao},

url = {https://www.computer.org/csdl/proceedings-article/icpr/2022/09956472/1IHpppIuqOc},

doi = {10.1109/ICPR56361.2022.9956472},

isbn = {978-1-66549-062-7},

year  = {2022},

date = {2022-08-01},

urldate = {2023-03-31},

pages = {542–549},

publisher = {IEEE Computer Society},

abstract = {Establishing dense correspondence between two images is a fundamental computer vision problem, which is typically tackled by matching local feature descriptors. However, without global awareness, such local features are often insufficient for disambiguating similar regions. And computing the pairwise feature correlation across images is both computation-expensive and memory-intensive. To make the local features aware of the global context and improve their matching accuracy, we introduce DenseGAP, a new solution for efficient Dense correspondence learning with a Graph-structured neural network conditioned on Anchor Points. Specifically, we first propose a graph structure that utilizes anchor points to provide sparse but reliable prior on inter- and intra-image context and propagates them to all image points via directed edges. We also design a graph-structured network to broadcast multi-level contexts via light-weighted message-passing layers and generate high-resolution feature maps at low memory cost. Finally, based on the predicted feature maps, we introduce a coarse-to-fine framework for accurate correspondence prediction using cycle consistency. Our feature descriptors capture both local and global information, thus enabling a continuous feature field for querying arbitrary points at high resolution. Through comprehensive ablative experiments and evaluations on large-scale indoor and outdoor datasets, we demonstrate that our method advances the state-of-the-art of correspondence learning on most benchmarks.},

keywords = {VGL},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gurney_robots_2022,

title = {Robots with Theory of Mind for Humans: A Survey},

author = {Nikolos Gurney and David V. Pynadath},

url = {https://ieeexplore.ieee.org/abstract/document/9900662},

doi = {10.1109/RO-MAN53752.2022.9900662},

year  = {2022},

date = {2022-08-01},

booktitle = {2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},

pages = {993–1000},

abstract = {Theory of Mind (ToM) is a psychological construct that captures the ability to ascribe mental states to others and then use those representations for explaining and predicting behavior. We review recent progress in endowing artificially intelligent robots with ToM. A broad array of modeling, experimental, and benchmarking approaches and methods are present in the extant literature. Unlike other domains of human cognition for which research has achieved super-human capabilities, ToM for robots lacks a unified construct and is not consistently benchmarked or validated—realities which possibly hinder progress in this domain. We argue that this is, at least in part, due to inconsistent defining of ToM, no presence of a unifying modeling construct, and the absence of a shared data resource. We believe these would improve the ability of the research community to compare the ToM abilities of different systems. We suggest that establishing a shared definition of ToM, creating a shared data resource that supports consistent benchmarking & validation, and developing a generalized modeling tool are critical steps towards giving robots ToM capabilities that lay observers will recognize as such.},

note = {ISSN: 1944-9437},

keywords = {Social Simulation, UARC},

pubstate = {published},

tppubtype = {inproceedings}

}