Publications
Search
Greenwald, Eric; Krakowski, Ari; Hurt, Timothy; Grindstaff, Kelly; Wang, Ning
It's like I'm the AI: Youth Sensemaking About AI through Metacognitive Embodiment Proceedings Article
In: Proceedings of the 23rd Annual ACM Interaction Design and Children Conference, pp. 789–793, ACM, Delft Netherlands, 2024, ISBN: 9798400704420.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chen, Meida; Lal, Devashish; Yu, Zifan; Xu, Jiuyi; Feng, Andrew; You, Suya; Nurunnabi, Abdul; Shi, Yangming
Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation Journal Article
In: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLVIII-2-2024, pp. 49–54, 2024, ISSN: 2194-9034.
@article{chen_large-scale_2024,
title = {Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation},
author = {Meida Chen and Devashish Lal and Zifan Yu and Jiuyi Xu and Andrew Feng and Suya You and Abdul Nurunnabi and Yangming Shi},
url = {https://isprs-archives.copernicus.org/articles/XLVIII-2-2024/49/2024/},
doi = {10.5194/isprs-archives-XLVIII-2-2024-49-2024},
issn = {2194-9034},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-20},
journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
volume = {XLVIII-2-2024},
pages = {49–54},
abstract = {Abstract. The fusion of low-cost unmanned aerial systems (UAS) with advanced photogrammetric techniques has revolutionized 3D terrain reconstruction, enabling the automated creation of detailed models. Concurrently, the advent of 3D Gaussian Splatting has introduced a paradigm shift in 3D data representation, offering visually realistic renditions distinct from traditional polygon-based models. Our research builds upon this foundation, aiming to integrate Gaussian Splatting into interactive simulations for immersive virtual environments. We address challenges such as collision detection by adopting a hybrid approach, combining Gaussian Splatting with photogrammetry-derived meshes. Through comprehensive experimentation covering varying terrain sizes and Gaussian densities, we evaluate scalability, performance, and limitations. Our findings contribute to advancing the use of advanced computer graphics techniques for enhanced 3D terrain visualization and simulation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lukin, Stephanie M; Bonial, Claire; Marge, Matthew; Hudson, Taylor; Hayes, Cory J.; Pollard, Kimberly; Baker, Anthony L.; Foots, Ashley; Artstein, Ron; Gervits, Felix; Abrams, Mitchell; Cassidy, Henry; Donatelli, Lucia; Leuski, Anton; Hill, Susan G.; Traum, David; Voss, Clare
SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus Journal Article
In: pp. 14445 - 144458, 2024.
@article{lukin-etal-2024-scout-situated,
title = {SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus},
author = {Stephanie M Lukin and Claire Bonial and Matthew Marge and Taylor Hudson and Cory J. Hayes and Kimberly Pollard and Anthony L. Baker and Ashley Foots and Ron Artstein and Felix Gervits and Mitchell Abrams and Henry Cassidy and Lucia Donatelli and Anton Leuski and Susan G. Hill and David Traum and Clare Voss},
url = {https://aclanthology.org/2024.lrec-main.1259},
year = {2024},
date = {2024-05-01},
pages = {14445 - 144458},
abstract = {We introduce the Situated Corpus Of Understanding Transactions (SCOUT), a multi-modal collection of human-robot dialogue in the task domain of collaborative exploration. The corpus was constructed from multiple Wizard-of-Oz experiments where human participants gave verbal instructions to a remotely-located robot to move and gather information about its surroundings. SCOUT contains 89,056 utterances and 310,095 words from 278 dialogues averaging 320 utterances per dialogue. The dialogues are aligned with the multi-modal data streams available during the experiments: 5,785 images and 30 maps. The corpus has been annotated with Abstract Meaning Representation and Dialogue-AMR to identify the speaker’s intent and meaning within an utterance, and with Transactional Units and Relations to track relationships between utterances to reveal patterns of the Dialogue Structure. We describe how the corpus and its annotations have been used to develop autonomous human-robot systems and enable research in open questions of how humans speak to robots. We release this corpus to accelerate progress in autonomous, situated, human-robot dialogue, especially in the context of navigation tasks where details about the environment need to be discovered.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
West, Taylor Nicole; Prinzing, Michael; Garton, Catherine; Berman, Catherine J.; Zhou, Jieni; Hale, James; Gratch, Jonathan; Fredrickson, Barbara
2024.
@misc{west_improving_2024,
title = {Improving Social Connection with Weak Ties and Strangers: Effects of a New Micro-Intervention on Interaction Quality and Social Behavior},
author = {Taylor Nicole West and Michael Prinzing and Catherine Garton and Catherine J. Berman and Jieni Zhou and James Hale and Jonathan Gratch and Barbara Fredrickson},
url = {https://osf.io/ytjr6},
doi = {10.31234/osf.io/ytjr6},
year = {2024},
date = {2024-05-01},
urldate = {2024-06-25},
abstract = {We propose that the emotional quality of people’s interactions with acquaintances (i.e., weak ties) and strangers contributes to well-being. We test whether a new micro-intervention can raise the quality of these interactions. We randomized young adults (N = 335) to this connectedness micro-intervention or a control intervention. Both interventions were delivered via a psychoeducational video followed by a brief conversation with a virtual human, with whom participants developed if-then plans to carry out their assigned behavioral goal. Pre-intervention, high-quality weak-tie and stranger interactions were associated with lower loneliness and greater mental health independent of strong-tie interaction quality. Experimental data showed the connectedness intervention improved the emotional quality of participants' interactions with weak ties and strangers over two days, evident in participants’ episodic self-reports and faster in-lab conversational response time. Discussion centers on implications for developing scalable behavioral interventions to improve well-being.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Jones, Brennan; Xu, Yan; Li, Qisheng; Scherer, Stefan
Designing a Proactive Context-Aware AI Chatbot for People's Long-Term Goals Proceedings Article
In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–7, ACM, Honolulu HI USA, 2024, ISBN: 9798400703317.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chemburkar, Ankur; Gordon, Andrew; Feng, Andrew
Evaluating Vision-Language Models on the TriangleCOPA Benchmark Journal Article
In: FLAIRS-37, vol. 37, 2024.
@article{chemburkar_evaluating_2024,
title = {Evaluating Vision-Language Models on the TriangleCOPA Benchmark},
author = {Ankur Chemburkar and Andrew Gordon and Andrew Feng},
year = {2024},
date = {2024-05-01},
journal = {FLAIRS-37},
volume = {37},
abstract = {The TriangleCOPA benchmark consists of 100 textual questions with videos depicting the movements of simple shapes in the style of the classic social-psychology film created by Fritz Heider and Marianne Simmel in 1944. In our experiments, we investigate the performance of current vision-language models on this challenging benchmark, assessing the capability of these models for visual anthropomorphism and abstract interpretation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mozgai, Sharon A; Kaurloto, Cari; Winn, Jade G; Leeds, Andrew; Beland, Sarah; Sookiassian, Arman; Hartholt, Arno
Accelerating Scoping Reviews: A Case Study in the User-Centered Design of an AI-Enabled Interdisciplinary Research Tool Proceedings Article
In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–8, ACM, Honolulu HI USA, 2024, ISBN: 9798400703317.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Soleymani, Mohammad; Kumano, Shiro; Provost, Emily Mower; Bianchi-Berthouze, Nadia; Sano, Akane; Suzuki, Kenji
Guest Editorial Best of ACII 2021 Journal Article
In: IEEE Transactions on Affective Computing, vol. 15, no. 2, pp. 376–379, 2024, ISSN: 1949-3045, 2371-9850.
@article{soleymani_guest_2024,
title = {Guest Editorial Best of ACII 2021},
author = {Mohammad Soleymani and Shiro Kumano and Emily Mower Provost and Nadia Bianchi-Berthouze and Akane Sano and Kenji Suzuki},
url = {https://ieeexplore.ieee.org/document/10542496/},
doi = {10.1109/TAFFC.2024.3389249},
issn = {1949-3045, 2371-9850},
year = {2024},
date = {2024-04-01},
urldate = {2024-06-25},
journal = {IEEE Transactions on Affective Computing},
volume = {15},
number = {2},
pages = {376–379},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Hui; Kuang, Bingran; Zhao, Yajie
Camera Calibration using a Single View of a Symmetric Object Proceedings Article
In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2705–2709, IEEE, Seoul, Korea, Republic of, 2024, ISBN: 9798350344851.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Goh, Crystal; Ma, Yu; Rizzo, Albert
Normative performance data on visual attention in neurotypical children: virtual reality assessment of cognitive and psychomotor development Journal Article
In: Frontiers in Virtual Reality, vol. 5, pp. 1309176, 2024, ISSN: 2673-4192.
@article{goh_normative_2024,
title = {Normative performance data on visual attention in neurotypical children: virtual reality assessment of cognitive and psychomotor development},
author = {Crystal Goh and Yu Ma and Albert Rizzo},
url = {https://www.frontiersin.org/articles/10.3389/frvir.2024.1309176/full},
doi = {10.3389/frvir.2024.1309176},
issn = {2673-4192},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-16},
journal = {Frontiers in Virtual Reality},
volume = {5},
pages = {1309176},
abstract = {Introduction:
Virtual Reality (VR) is revolutionizing healthcare research and practice by offering innovative methodologies across various clinical conditions. Advances in VR technology enable the creation of controllable, multisensory 3D environments, making it an appealing tool for capturing and quantifying behavior in realistic scenarios. This paper details the application of VR as a tool for neurocognitive evaluation, specifically in attention process assessment, an area of relevance for informing the diagnosis of childhood health conditions such as Attention Deficit Hyperactivity Disorder (ADHD).
Methods:
The data presented focuses on attention performance results from a large sample (
n = 837) of neurotypical male and female children (ages 6–13) tested on a visual continuous performance task, administered within an immersive VR classroom environment. This data was collected to create a normative baseline database for use to inform comparisons with the performances of children with ADHD to support diagnostic decision-making in this area.
Results:
Results indicate systematic improvements on most metrics across the age span, and sex differences are noted on key variables thought to reflect differential measures of hyperactivity and inattention in children with ADHD. Results support VR technology as a safe and viable option for testing attention processes in children, under stimulus conditions that closely mimic ecologically relevant challenges found in everyday life.
Discussion:
In response to these stimulus conditions, VR can support advanced methods for capturing and quantifying users’ behavioral responses. VR offers a more systematic and objective approach for clinical assessment and intervention and provides conceptual support for its use in a wide variety of healthcare contexts.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Virtual Reality (VR) is revolutionizing healthcare research and practice by offering innovative methodologies across various clinical conditions. Advances in VR technology enable the creation of controllable, multisensory 3D environments, making it an appealing tool for capturing and quantifying behavior in realistic scenarios. This paper details the application of VR as a tool for neurocognitive evaluation, specifically in attention process assessment, an area of relevance for informing the diagnosis of childhood health conditions such as Attention Deficit Hyperactivity Disorder (ADHD).
Methods:
The data presented focuses on attention performance results from a large sample (
n = 837) of neurotypical male and female children (ages 6–13) tested on a visual continuous performance task, administered within an immersive VR classroom environment. This data was collected to create a normative baseline database for use to inform comparisons with the performances of children with ADHD to support diagnostic decision-making in this area.
Results:
Results indicate systematic improvements on most metrics across the age span, and sex differences are noted on key variables thought to reflect differential measures of hyperactivity and inattention in children with ADHD. Results support VR technology as a safe and viable option for testing attention processes in children, under stimulus conditions that closely mimic ecologically relevant challenges found in everyday life.
Discussion:
In response to these stimulus conditions, VR can support advanced methods for capturing and quantifying users’ behavioral responses. VR offers a more systematic and objective approach for clinical assessment and intervention and provides conceptual support for its use in a wide variety of healthcare contexts.
Gurney, Nikolos; Loewenstein, George; Chater, Nick
Conversational technology and reactions to withheld information Journal Article
In: PLOS ONE, vol. 19, no. 4, pp. e0301382, 2024, ISSN: 1932-6203.
@article{gurney_conversational_2024,
title = {Conversational technology and reactions to withheld information},
author = {Nikolos Gurney and George Loewenstein and Nick Chater},
editor = {Petre Caraiani},
url = {https://dx.plos.org/10.1371/journal.pone.0301382},
doi = {10.1371/journal.pone.0301382},
issn = {1932-6203},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-16},
journal = {PLOS ONE},
volume = {19},
number = {4},
pages = {e0301382},
abstract = {People frequently face decisions that require making inferences about withheld information. The advent of large language models coupled with conversational technology, e.g., Alexa, Siri, Cortana, and the Google Assistant, is changing the mode in which people make these inferences. We demonstrate that conversational modes of information provision, relative to traditional digital media, result in more critical responses to withheld information, including: (1) a reduction in evaluations of a product or service for which information is withheld and (2) an increased likelihood of recalling that information was withheld. These effects are robust across multiple conversational modes: a recorded phone conversation, an unfolding chat conversation, and a conversation script. We provide further evidence that these effects hold for conversations with the Google Assistant, a prominent conversational technology. The experimental results point to participants’ intuitions about why the information was withheld as the driver of the effect.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Gordon, Andrew S.; Feng, Andrew
Combining the Predictions of Out-of-Domain Classifiers Using Etcetera Abduction Proceedings Article
In: 2024 58th Annual Conference on Information Sciences and Systems (CISS), pp. 1–6, IEEE, Princeton, NJ, USA, 2024, ISBN: 9798350369298.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Frummet, Alexander; Speggiorin, Alessandro; Elsweiler, David; Leuski, Anton; Dalton, Jeff
Cooking with Conversation: Enhancing User Engagement and Learning with a Knowledge-Enhancing Assistant Journal Article
In: ACM Transactions on Information Systems, pp. 3649500, 2024, ISSN: 1046-8188, 1558-2868.
@article{frummet_cooking_2024,
title = {Cooking with Conversation: Enhancing User Engagement and Learning with a Knowledge-Enhancing Assistant},
author = {Alexander Frummet and Alessandro Speggiorin and David Elsweiler and Anton Leuski and Jeff Dalton},
url = {https://dl.acm.org/doi/10.1145/3649500},
doi = {10.1145/3649500},
issn = {1046-8188, 1558-2868},
year = {2024},
date = {2024-03-01},
urldate = {2024-04-16},
journal = {ACM Transactions on Information Systems},
pages = {3649500},
abstract = {We present two empirical studies to investigate users’ expectations and behaviours when using digital assistants, such as Alexa and Google Home, in a kitchen context: First, a survey (N=200) queries participants on their expectations for the kinds of information that such systems should be able to provide. While consensus exists on expecting information about cooking steps and processes, younger participants who enjoy cooking express a higher likelihood of expecting details on food history or the science of cooking. In a follow-up Wizard-of-Oz study (N = 48), users were guided through the steps of a recipe either by an
active
wizard that alerted participants to information it could provide or a
passive
wizard who only answered questions that were provided by the user. The
active
policy led to almost double the number of conversational utterances and 1.5 times more knowledge-related user questions compared to the
passive
policy. Also, it resulted in 1.7 times more knowledge communicated than the
passive
policy. We discuss the findings in the context of related work and reveal implications for the design and use of such assistants for cooking and other purposes such as DIY and craft tasks, as well as the lessons we learned for evaluating such systems.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
active
wizard that alerted participants to information it could provide or a
passive
wizard who only answered questions that were provided by the user. The
active
policy led to almost double the number of conversational utterances and 1.5 times more knowledge-related user questions compared to the
passive
policy. Also, it resulted in 1.7 times more knowledge communicated than the
passive
policy. We discuss the findings in the context of related work and reveal implications for the design and use of such assistants for cooking and other purposes such as DIY and craft tasks, as well as the lessons we learned for evaluating such systems.
Lu, Liupei; Yin, Yufeng; Gu, Yuming; Wu, Yizhen; Prasad, Pratusha; Zhao, Yajie; Soleymani, Mohammad
Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection Miscellaneous
2024, (arXiv:2403.10737 [cs]).
@misc{lu_leveraging_2024,
title = {Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection},
author = {Liupei Lu and Yufeng Yin and Yuming Gu and Yizhen Wu and Pratusha Prasad and Yajie Zhao and Mohammad Soleymani},
url = {http://arxiv.org/abs/2403.10737},
year = {2024},
date = {2024-03-01},
urldate = {2024-04-16},
publisher = {arXiv},
abstract = {Facial action unit (AU) detection is a fundamental block for objective facial expression analysis. Supervised learning approaches require a large amount of manual labeling which is costly. The limited labeled data are also not diverse in terms of gender which can affect model fairness. In this paper, we propose to use synthetically generated data and multi-source domain adaptation (MSDA) to address the problems of the scarcity of labeled data and the diversity of subjects. Specifically, we propose to generate a diverse dataset through synthetic facial expression re-targeting by transferring the expressions from real faces to synthetic avatars. Then, we use MSDA to transfer the AU detection knowledge from a real dataset and the synthetic dataset to a target dataset. Instead of aligning the overall distributions of different domains, we propose Paired Moment Matching (PM2) to align the features of the paired real and synthetic data with the same facial expression. To further improve gender fairness, PM2 matches the features of the real data with a female and a male synthetic image. Our results indicate that synthetic data and the proposed model improve both AU detection performance and fairness across genders, demonstrating its potential to solve AU detection in-the-wild.},
note = {arXiv:2403.10737 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Tran, Minh; Chang, Di; Siniukov, Maksim; Soleymani, Mohammad
Dyadic Interaction Modeling for Social Behavior Generation Miscellaneous
2024, (arXiv:2403.09069 [cs]).
@misc{tran_dyadic_2024,
title = {Dyadic Interaction Modeling for Social Behavior Generation},
author = {Minh Tran and Di Chang and Maksim Siniukov and Mohammad Soleymani},
url = {http://arxiv.org/abs/2403.09069},
year = {2024},
date = {2024-03-01},
urldate = {2024-03-19},
publisher = {arXiv},
abstract = {Human-human communication is like a delicate dance where listeners and speakers concurrently interact to maintain conversational dynamics. Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction. In this paper, we present an effective framework for creating 3D facial motions in dyadic interactions. Existing work consider a listener as a reactive agent with reflexive behaviors to the speaker's voice and facial motions. The heart of our framework is Dyadic Interaction Modeling (DIM), a pre-training approach that jointly models speakers' and listeners' motions through masking and contrastive learning to learn representations that capture the dyadic context. To enable the generation of non-deterministic behaviors, we encode both listener and speaker motions into discrete latent representations, through VQ-VAE. The pre-trained model is further fine-tuned for motion generation. Extensive experiments demonstrate the superiority of our framework in generating listener motions, establishing a new state-of-the-art according to the quantitative measures capturing the diversity and realism of generated motions. Qualitative results demonstrate the superior capabilities of the proposed approach in generating diverse and realistic expressions, eye blinks and head gestures.},
note = {arXiv:2403.09069 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Kwon, Deuksin; Weiss, Emily; Kulshrestha, Tara; Chawla, Kushal; Lucas, Gale M.; Gratch, Jonathan
Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues Miscellaneous
2024, (arXiv:2402.13550 [cs]).
@misc{kwon_are_2024,
title = {Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues},
author = {Deuksin Kwon and Emily Weiss and Tara Kulshrestha and Kushal Chawla and Gale M. Lucas and Jonathan Gratch},
url = {http://arxiv.org/abs/2402.13550},
year = {2024},
date = {2024-02-01},
urldate = {2024-03-14},
publisher = {arXiv},
abstract = {A successful negotiation demands a deep comprehension of the conversation context, Theory-of-Mind (ToM) skills to infer the partner's motives, as well as strategic reasoning and effective communication, making it challenging for automated systems. Given the remarkable performance of LLMs across a variety of NLP tasks, in this work, we aim to understand how LLMs can advance different aspects of negotiation research, ranging from designing dialogue systems to providing pedagogical feedback and scaling up data collection practices. To this end, we devise a methodology to analyze the multifaceted capabilities of LLMs across diverse dialogue scenarios covering all the time stages of a typical negotiation interaction. Our analysis adds to the increasing evidence for the superiority of GPT-4 across various tasks while also providing insights into specific tasks that remain difficult for LLMs. For instance, the models correlate poorly with human players when making subjective assessments about the negotiation dialogues and often struggle to generate responses that are contextually appropriate as well as strategically advantageous.},
note = {arXiv:2402.13550 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Marti, Deniz; Hanrahan, David; Sanchez-Triana, Ernesto; Wells, Mona; Corra, Lilian; Hu, Howard; Breysse, Patrick N.; Laborde, Amalia; Caravanos, Jack; Bertollini, Roberto; Porterfield, Kate; Fuller, Richard
Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals Technical Report
Public and Global Health 2024.
@techreport{marti_structured_2024,
title = {Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals},
author = {Deniz Marti and David Hanrahan and Ernesto Sanchez-Triana and Mona Wells and Lilian Corra and Howard Hu and Patrick N. Breysse and Amalia Laborde and Jack Caravanos and Roberto Bertollini and Kate Porterfield and Richard Fuller},
url = {http://medrxiv.org/lookup/doi/10.1101/2024.01.30.24301863},
doi = {10.1101/2024.01.30.24301863},
year = {2024},
date = {2024-02-01},
urldate = {2024-02-21},
institution = {Public and Global Health},
abstract = {ABSTRACT
Introduction
Chemical contamination and pollution are an ongoing threat to human health and the environment. The concern over the consequences of chemical exposures at the global level continues to grow. Because resources are constrained, there is a need to prioritize interventions focused on the greatest health impact. Data, especially related to chemical exposures, are rarely available for most substances of concern, and alternate methods to evaluate their impact are needed.
Structured Expert Judgment (SEJ) Process
A Structured Expert Judgment
3
process was performed to provide plausible estimates of health impacts for 16 commonly found pollutants: asbestos, arsenic, benzene, chromium, cadmium, dioxins, fluoride, highly hazardous pesticides (HHPs), lead, mercury, polycyclic-aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), Per- and Polyfluorinated Substances (PFAs), phthalates, endocrine disrupting chemicals (EDCs), and brominated flame retardants (BRFs). This process, undertaken by sector experts, weighed individual estimations of the probable global health scale health impacts of each pollutant using objective estimates of the expert opinions’ statistical accuracy and informativeness.
Main Findings
The foremost substances, in terms of mean projected annual total deaths, were lead, asbestos, arsenic, and HHPs. Lead surpasses the others by a large margin, with an estimated median value of 1.7 million deaths annually. The three other substances averaged between 136,000 and 274,000 deaths per year. Of the 12 other chemicals evaluated, none reached an estimated annual death count exceeding 100,000. These findings underscore the importance of prioritizing available resources on reducing and remediating the impacts of these key pollutants.
Range of Health Impacts
Based on the evidence available, experts concluded some of the more notorious chemical pollutants, such as PCBs and dioxin, do not result in high levels of human health impact from a global scale perspective. However, the chemical toxicity of some compounds released in recent decades, such as Endocrine Disrupters and PFAs, cannot be ignored, even if current impacts are limited. Moreover, the impact of some chemicals may be disproportionately large in some geographic areas. Continued research and monitoring are essential; and a preventative approach is needed for chemicals.
Future Directions
These results, and potential similar analyses of other chemicals, are provided as inputs to ongoing discussions about priority setting for global chemicals and pollution management. Furthermore, we suggest that this SEJ process be repeated periodically as new information becomes available.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Introduction
Chemical contamination and pollution are an ongoing threat to human health and the environment. The concern over the consequences of chemical exposures at the global level continues to grow. Because resources are constrained, there is a need to prioritize interventions focused on the greatest health impact. Data, especially related to chemical exposures, are rarely available for most substances of concern, and alternate methods to evaluate their impact are needed.
Structured Expert Judgment (SEJ) Process
A Structured Expert Judgment
3
process was performed to provide plausible estimates of health impacts for 16 commonly found pollutants: asbestos, arsenic, benzene, chromium, cadmium, dioxins, fluoride, highly hazardous pesticides (HHPs), lead, mercury, polycyclic-aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), Per- and Polyfluorinated Substances (PFAs), phthalates, endocrine disrupting chemicals (EDCs), and brominated flame retardants (BRFs). This process, undertaken by sector experts, weighed individual estimations of the probable global health scale health impacts of each pollutant using objective estimates of the expert opinions’ statistical accuracy and informativeness.
Main Findings
The foremost substances, in terms of mean projected annual total deaths, were lead, asbestos, arsenic, and HHPs. Lead surpasses the others by a large margin, with an estimated median value of 1.7 million deaths annually. The three other substances averaged between 136,000 and 274,000 deaths per year. Of the 12 other chemicals evaluated, none reached an estimated annual death count exceeding 100,000. These findings underscore the importance of prioritizing available resources on reducing and remediating the impacts of these key pollutants.
Range of Health Impacts
Based on the evidence available, experts concluded some of the more notorious chemical pollutants, such as PCBs and dioxin, do not result in high levels of human health impact from a global scale perspective. However, the chemical toxicity of some compounds released in recent decades, such as Endocrine Disrupters and PFAs, cannot be ignored, even if current impacts are limited. Moreover, the impact of some chemicals may be disproportionately large in some geographic areas. Continued research and monitoring are essential; and a preventative approach is needed for chemicals.
Future Directions
These results, and potential similar analyses of other chemicals, are provided as inputs to ongoing discussions about priority setting for global chemicals and pollution management. Furthermore, we suggest that this SEJ process be repeated periodically as new information becomes available.
Yu, Zifan; Tavakoli, Erfan Bank; Chen, Meida; You, Suya; Rao, Raghuveer; Agarwal, Sanjeev; Ren, Fengbo
TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection Miscellaneous
2024, (arXiv:2311.02535 [cs]).
@misc{yu_tokenmotion_2024,
title = {TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection},
author = {Zifan Yu and Erfan Bank Tavakoli and Meida Chen and Suya You and Raghuveer Rao and Sanjeev Agarwal and Fengbo Ren},
url = {http://arxiv.org/abs/2311.02535},
year = {2024},
date = {2024-02-01},
urldate = {2024-02-21},
publisher = {arXiv},
abstract = {The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD. It outperforms the existing state-of-the-art method by a 12.8% improvement in weighted F-measure, an 8.4% enhancement in S-measure, and a 10.7% boost in mean IoU. The results demonstrate the benefits of utilizing motion-guided features via learnable token selection within a transformer-based framework to tackle the intricate task of VCOD.},
note = {arXiv:2311.02535 [cs]},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Saxon, Leslie; Faulk, Robert T; Boberg, Jill; Barrett, Trevor; McLelland, Steve
In: Journal of Special Operations Medicine, 2024, ISSN: 1553-9768.
@article{saxon_continuous_2024,
title = {Continuous Assessment of Active-Duty Army Special Operations and Reconnaissance Marines Using Digital Devices and Custom Software: The Digital Comprehensive Operator Readiness Assessment (DcORA) Study},
author = {Leslie Saxon and Robert T Faulk and Jill Boberg and Trevor Barrett and Steve McLelland},
url = {https://www.jsomonline.org/Citations/PXKK-I23D.php},
doi = {10.55460/PXKK-I23D},
issn = {1553-9768},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-25},
journal = {Journal of Special Operations Medicine},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Hao; Chang, Di; Li, Fang; Soleymani, Mohammad; Ahuja, Narendra
MagicPose4D: Crafting Articulated Models with Appearance and Motion Control Miscellaneous
2024, (Version Number: 1).
@misc{zhang_magicpose4d_2024,
title = {MagicPose4D: Crafting Articulated Models with Appearance and Motion Control},
author = {Hao Zhang and Di Chang and Fang Li and Mohammad Soleymani and Narendra Ahuja},
url = {https://arxiv.org/abs/2405.14017},
doi = {10.48550/ARXIV.2405.14017},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-25},
publisher = {arXiv},
abstract = {With the success of 2D and 3D visual generative models, there is growing interest in generating 4D content. Existing methods primarily rely on text prompts to produce 4D content, but they often fall short of accurately defining complex or rare motions. To address this limitation, we propose MagicPose4D, a novel framework for refined control over both appearance and motion in 4D generation. Unlike traditional methods, MagicPose4D accepts monocular videos as motion prompts, enabling precise and customizable motion generation. MagicPose4D comprises two key modules:
i) Dual-Phase 4D Reconstruction Modulevphantom which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase refines the model using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations.
ii) Cross-category Motion Transfer Modulevphantom leverages the predictions from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training.
Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.},
note = {Version Number: 1},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
i) Dual-Phase 4D Reconstruction Modulevphantom which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase refines the model using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations.
ii) Cross-category Motion Transfer Modulevphantom leverages the predictions from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training.
Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.
Filter
2024
Greenwald, Eric; Krakowski, Ari; Hurt, Timothy; Grindstaff, Kelly; Wang, Ning
It's like I'm the AI: Youth Sensemaking About AI through Metacognitive Embodiment Proceedings Article
In: Proceedings of the 23rd Annual ACM Interaction Design and Children Conference, pp. 789–793, ACM, Delft Netherlands, 2024, ISBN: 9798400704420.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chen, Meida; Lal, Devashish; Yu, Zifan; Xu, Jiuyi; Feng, Andrew; You, Suya; Nurunnabi, Abdul; Shi, Yangming
Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation Journal Article
In: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLVIII-2-2024, pp. 49–54, 2024, ISSN: 2194-9034.
Abstract | Links | BibTeX | Tags:
@article{chen_large-scale_2024,
title = {Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation},
author = {Meida Chen and Devashish Lal and Zifan Yu and Jiuyi Xu and Andrew Feng and Suya You and Abdul Nurunnabi and Yangming Shi},
url = {https://isprs-archives.copernicus.org/articles/XLVIII-2-2024/49/2024/},
doi = {10.5194/isprs-archives-XLVIII-2-2024-49-2024},
issn = {2194-9034},
year = {2024},
date = {2024-06-01},
urldate = {2024-06-20},
journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
volume = {XLVIII-2-2024},
pages = {49–54},
abstract = {Abstract. The fusion of low-cost unmanned aerial systems (UAS) with advanced photogrammetric techniques has revolutionized 3D terrain reconstruction, enabling the automated creation of detailed models. Concurrently, the advent of 3D Gaussian Splatting has introduced a paradigm shift in 3D data representation, offering visually realistic renditions distinct from traditional polygon-based models. Our research builds upon this foundation, aiming to integrate Gaussian Splatting into interactive simulations for immersive virtual environments. We address challenges such as collision detection by adopting a hybrid approach, combining Gaussian Splatting with photogrammetry-derived meshes. Through comprehensive experimentation covering varying terrain sizes and Gaussian densities, we evaluate scalability, performance, and limitations. Our findings contribute to advancing the use of advanced computer graphics techniques for enhanced 3D terrain visualization and simulation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lukin, Stephanie M; Bonial, Claire; Marge, Matthew; Hudson, Taylor; Hayes, Cory J.; Pollard, Kimberly; Baker, Anthony L.; Foots, Ashley; Artstein, Ron; Gervits, Felix; Abrams, Mitchell; Cassidy, Henry; Donatelli, Lucia; Leuski, Anton; Hill, Susan G.; Traum, David; Voss, Clare
SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus Journal Article
In: pp. 14445 - 144458, 2024.
Abstract | Links | BibTeX | Tags:
@article{lukin-etal-2024-scout-situated,
title = {SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus},
author = {Stephanie M Lukin and Claire Bonial and Matthew Marge and Taylor Hudson and Cory J. Hayes and Kimberly Pollard and Anthony L. Baker and Ashley Foots and Ron Artstein and Felix Gervits and Mitchell Abrams and Henry Cassidy and Lucia Donatelli and Anton Leuski and Susan G. Hill and David Traum and Clare Voss},
url = {https://aclanthology.org/2024.lrec-main.1259},
year = {2024},
date = {2024-05-01},
pages = {14445 - 144458},
abstract = {We introduce the Situated Corpus Of Understanding Transactions (SCOUT), a multi-modal collection of human-robot dialogue in the task domain of collaborative exploration. The corpus was constructed from multiple Wizard-of-Oz experiments where human participants gave verbal instructions to a remotely-located robot to move and gather information about its surroundings. SCOUT contains 89,056 utterances and 310,095 words from 278 dialogues averaging 320 utterances per dialogue. The dialogues are aligned with the multi-modal data streams available during the experiments: 5,785 images and 30 maps. The corpus has been annotated with Abstract Meaning Representation and Dialogue-AMR to identify the speaker’s intent and meaning within an utterance, and with Transactional Units and Relations to track relationships between utterances to reveal patterns of the Dialogue Structure. We describe how the corpus and its annotations have been used to develop autonomous human-robot systems and enable research in open questions of how humans speak to robots. We release this corpus to accelerate progress in autonomous, situated, human-robot dialogue, especially in the context of navigation tasks where details about the environment need to be discovered.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
West, Taylor Nicole; Prinzing, Michael; Garton, Catherine; Berman, Catherine J.; Zhou, Jieni; Hale, James; Gratch, Jonathan; Fredrickson, Barbara
2024.
Abstract | Links | BibTeX | Tags: Emotions
@misc{west_improving_2024,
title = {Improving Social Connection with Weak Ties and Strangers: Effects of a New Micro-Intervention on Interaction Quality and Social Behavior},
author = {Taylor Nicole West and Michael Prinzing and Catherine Garton and Catherine J. Berman and Jieni Zhou and James Hale and Jonathan Gratch and Barbara Fredrickson},
url = {https://osf.io/ytjr6},
doi = {10.31234/osf.io/ytjr6},
year = {2024},
date = {2024-05-01},
urldate = {2024-06-25},
abstract = {We propose that the emotional quality of people’s interactions with acquaintances (i.e., weak ties) and strangers contributes to well-being. We test whether a new micro-intervention can raise the quality of these interactions. We randomized young adults (N = 335) to this connectedness micro-intervention or a control intervention. Both interventions were delivered via a psychoeducational video followed by a brief conversation with a virtual human, with whom participants developed if-then plans to carry out their assigned behavioral goal. Pre-intervention, high-quality weak-tie and stranger interactions were associated with lower loneliness and greater mental health independent of strong-tie interaction quality. Experimental data showed the connectedness intervention improved the emotional quality of participants' interactions with weak ties and strangers over two days, evident in participants’ episodic self-reports and faster in-lab conversational response time. Discussion centers on implications for developing scalable behavioral interventions to improve well-being.},
keywords = {Emotions},
pubstate = {published},
tppubtype = {misc}
}
Jones, Brennan; Xu, Yan; Li, Qisheng; Scherer, Stefan
Designing a Proactive Context-Aware AI Chatbot for People's Long-Term Goals Proceedings Article
In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–7, ACM, Honolulu HI USA, 2024, ISBN: 9798400703317.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chemburkar, Ankur; Gordon, Andrew; Feng, Andrew
Evaluating Vision-Language Models on the TriangleCOPA Benchmark Journal Article
In: FLAIRS-37, vol. 37, 2024.
@article{chemburkar_evaluating_2024,
title = {Evaluating Vision-Language Models on the TriangleCOPA Benchmark},
author = {Ankur Chemburkar and Andrew Gordon and Andrew Feng},
year = {2024},
date = {2024-05-01},
journal = {FLAIRS-37},
volume = {37},
abstract = {The TriangleCOPA benchmark consists of 100 textual questions with videos depicting the movements of simple shapes in the style of the classic social-psychology film created by Fritz Heider and Marianne Simmel in 1944. In our experiments, we investigate the performance of current vision-language models on this challenging benchmark, assessing the capability of these models for visual anthropomorphism and abstract interpretation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mozgai, Sharon A; Kaurloto, Cari; Winn, Jade G; Leeds, Andrew; Beland, Sarah; Sookiassian, Arman; Hartholt, Arno
Accelerating Scoping Reviews: A Case Study in the User-Centered Design of an AI-Enabled Interdisciplinary Research Tool Proceedings Article
In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1–8, ACM, Honolulu HI USA, 2024, ISBN: 9798400703317.
Links | BibTeX | Tags: AI, UARC, Virtual Humans
@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, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Soleymani, Mohammad; Kumano, Shiro; Provost, Emily Mower; Bianchi-Berthouze, Nadia; Sano, Akane; Suzuki, Kenji
Guest Editorial Best of ACII 2021 Journal Article
In: IEEE Transactions on Affective Computing, vol. 15, no. 2, pp. 376–379, 2024, ISSN: 1949-3045, 2371-9850.
@article{soleymani_guest_2024,
title = {Guest Editorial Best of ACII 2021},
author = {Mohammad Soleymani and Shiro Kumano and Emily Mower Provost and Nadia Bianchi-Berthouze and Akane Sano and Kenji Suzuki},
url = {https://ieeexplore.ieee.org/document/10542496/},
doi = {10.1109/TAFFC.2024.3389249},
issn = {1949-3045, 2371-9850},
year = {2024},
date = {2024-04-01},
urldate = {2024-06-25},
journal = {IEEE Transactions on Affective Computing},
volume = {15},
number = {2},
pages = {376–379},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhang, Hui; Kuang, Bingran; Zhao, Yajie
Camera Calibration using a Single View of a Symmetric Object Proceedings Article
In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2705–2709, IEEE, Seoul, Korea, Republic of, 2024, ISBN: 9798350344851.
Links | BibTeX | Tags: Graphics
@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},
pubstate = {published},
tppubtype = {inproceedings}
}
Goh, Crystal; Ma, Yu; Rizzo, Albert
Normative performance data on visual attention in neurotypical children: virtual reality assessment of cognitive and psychomotor development Journal Article
In: Frontiers in Virtual Reality, vol. 5, pp. 1309176, 2024, ISSN: 2673-4192.
Abstract | Links | BibTeX | Tags: MedVR
@article{goh_normative_2024,
title = {Normative performance data on visual attention in neurotypical children: virtual reality assessment of cognitive and psychomotor development},
author = {Crystal Goh and Yu Ma and Albert Rizzo},
url = {https://www.frontiersin.org/articles/10.3389/frvir.2024.1309176/full},
doi = {10.3389/frvir.2024.1309176},
issn = {2673-4192},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-16},
journal = {Frontiers in Virtual Reality},
volume = {5},
pages = {1309176},
abstract = {Introduction:
Virtual Reality (VR) is revolutionizing healthcare research and practice by offering innovative methodologies across various clinical conditions. Advances in VR technology enable the creation of controllable, multisensory 3D environments, making it an appealing tool for capturing and quantifying behavior in realistic scenarios. This paper details the application of VR as a tool for neurocognitive evaluation, specifically in attention process assessment, an area of relevance for informing the diagnosis of childhood health conditions such as Attention Deficit Hyperactivity Disorder (ADHD).
Methods:
The data presented focuses on attention performance results from a large sample (
n = 837) of neurotypical male and female children (ages 6–13) tested on a visual continuous performance task, administered within an immersive VR classroom environment. This data was collected to create a normative baseline database for use to inform comparisons with the performances of children with ADHD to support diagnostic decision-making in this area.
Results:
Results indicate systematic improvements on most metrics across the age span, and sex differences are noted on key variables thought to reflect differential measures of hyperactivity and inattention in children with ADHD. Results support VR technology as a safe and viable option for testing attention processes in children, under stimulus conditions that closely mimic ecologically relevant challenges found in everyday life.
Discussion:
In response to these stimulus conditions, VR can support advanced methods for capturing and quantifying users’ behavioral responses. VR offers a more systematic and objective approach for clinical assessment and intervention and provides conceptual support for its use in a wide variety of healthcare contexts.},
keywords = {MedVR},
pubstate = {published},
tppubtype = {article}
}
Virtual Reality (VR) is revolutionizing healthcare research and practice by offering innovative methodologies across various clinical conditions. Advances in VR technology enable the creation of controllable, multisensory 3D environments, making it an appealing tool for capturing and quantifying behavior in realistic scenarios. This paper details the application of VR as a tool for neurocognitive evaluation, specifically in attention process assessment, an area of relevance for informing the diagnosis of childhood health conditions such as Attention Deficit Hyperactivity Disorder (ADHD).
Methods:
The data presented focuses on attention performance results from a large sample (
n = 837) of neurotypical male and female children (ages 6–13) tested on a visual continuous performance task, administered within an immersive VR classroom environment. This data was collected to create a normative baseline database for use to inform comparisons with the performances of children with ADHD to support diagnostic decision-making in this area.
Results:
Results indicate systematic improvements on most metrics across the age span, and sex differences are noted on key variables thought to reflect differential measures of hyperactivity and inattention in children with ADHD. Results support VR technology as a safe and viable option for testing attention processes in children, under stimulus conditions that closely mimic ecologically relevant challenges found in everyday life.
Discussion:
In response to these stimulus conditions, VR can support advanced methods for capturing and quantifying users’ behavioral responses. VR offers a more systematic and objective approach for clinical assessment and intervention and provides conceptual support for its use in a wide variety of healthcare contexts.
Gurney, Nikolos; Loewenstein, George; Chater, Nick
Conversational technology and reactions to withheld information Journal Article
In: PLOS ONE, vol. 19, no. 4, pp. e0301382, 2024, ISSN: 1932-6203.
Abstract | Links | BibTeX | Tags: DTIC, Social Simulation, UARC
@article{gurney_conversational_2024,
title = {Conversational technology and reactions to withheld information},
author = {Nikolos Gurney and George Loewenstein and Nick Chater},
editor = {Petre Caraiani},
url = {https://dx.plos.org/10.1371/journal.pone.0301382},
doi = {10.1371/journal.pone.0301382},
issn = {1932-6203},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-16},
journal = {PLOS ONE},
volume = {19},
number = {4},
pages = {e0301382},
abstract = {People frequently face decisions that require making inferences about withheld information. The advent of large language models coupled with conversational technology, e.g., Alexa, Siri, Cortana, and the Google Assistant, is changing the mode in which people make these inferences. We demonstrate that conversational modes of information provision, relative to traditional digital media, result in more critical responses to withheld information, including: (1) a reduction in evaluations of a product or service for which information is withheld and (2) an increased likelihood of recalling that information was withheld. These effects are robust across multiple conversational modes: a recorded phone conversation, an unfolding chat conversation, and a conversation script. We provide further evidence that these effects hold for conversations with the Google Assistant, a prominent conversational technology. The experimental results point to participants’ intuitions about why the information was withheld as the driver of the effect.},
keywords = {DTIC, Social Simulation, UARC},
pubstate = {published},
tppubtype = {article}
}
Gordon, Andrew S.; Feng, Andrew
Combining the Predictions of Out-of-Domain Classifiers Using Etcetera Abduction Proceedings Article
In: 2024 58th Annual Conference on Information Sciences and Systems (CISS), pp. 1–6, IEEE, Princeton, NJ, USA, 2024, ISBN: 9798350369298.
Links | BibTeX | Tags: DTIC, Narrative, The Narrative Group, UARC
@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}
}
Frummet, Alexander; Speggiorin, Alessandro; Elsweiler, David; Leuski, Anton; Dalton, Jeff
Cooking with Conversation: Enhancing User Engagement and Learning with a Knowledge-Enhancing Assistant Journal Article
In: ACM Transactions on Information Systems, pp. 3649500, 2024, ISSN: 1046-8188, 1558-2868.
Abstract | Links | BibTeX | Tags: DTIC, Natural Language, UARC
@article{frummet_cooking_2024,
title = {Cooking with Conversation: Enhancing User Engagement and Learning with a Knowledge-Enhancing Assistant},
author = {Alexander Frummet and Alessandro Speggiorin and David Elsweiler and Anton Leuski and Jeff Dalton},
url = {https://dl.acm.org/doi/10.1145/3649500},
doi = {10.1145/3649500},
issn = {1046-8188, 1558-2868},
year = {2024},
date = {2024-03-01},
urldate = {2024-04-16},
journal = {ACM Transactions on Information Systems},
pages = {3649500},
abstract = {We present two empirical studies to investigate users’ expectations and behaviours when using digital assistants, such as Alexa and Google Home, in a kitchen context: First, a survey (N=200) queries participants on their expectations for the kinds of information that such systems should be able to provide. While consensus exists on expecting information about cooking steps and processes, younger participants who enjoy cooking express a higher likelihood of expecting details on food history or the science of cooking. In a follow-up Wizard-of-Oz study (N = 48), users were guided through the steps of a recipe either by an
active
wizard that alerted participants to information it could provide or a
passive
wizard who only answered questions that were provided by the user. The
active
policy led to almost double the number of conversational utterances and 1.5 times more knowledge-related user questions compared to the
passive
policy. Also, it resulted in 1.7 times more knowledge communicated than the
passive
policy. We discuss the findings in the context of related work and reveal implications for the design and use of such assistants for cooking and other purposes such as DIY and craft tasks, as well as the lessons we learned for evaluating such systems.},
keywords = {DTIC, Natural Language, UARC},
pubstate = {published},
tppubtype = {article}
}
active
wizard that alerted participants to information it could provide or a
passive
wizard who only answered questions that were provided by the user. The
active
policy led to almost double the number of conversational utterances and 1.5 times more knowledge-related user questions compared to the
passive
policy. Also, it resulted in 1.7 times more knowledge communicated than the
passive
policy. We discuss the findings in the context of related work and reveal implications for the design and use of such assistants for cooking and other purposes such as DIY and craft tasks, as well as the lessons we learned for evaluating such systems.
Lu, Liupei; Yin, Yufeng; Gu, Yuming; Wu, Yizhen; Prasad, Pratusha; Zhao, Yajie; Soleymani, Mohammad
Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection Miscellaneous
2024, (arXiv:2403.10737 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@misc{lu_leveraging_2024,
title = {Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection},
author = {Liupei Lu and Yufeng Yin and Yuming Gu and Yizhen Wu and Pratusha Prasad and Yajie Zhao and Mohammad Soleymani},
url = {http://arxiv.org/abs/2403.10737},
year = {2024},
date = {2024-03-01},
urldate = {2024-04-16},
publisher = {arXiv},
abstract = {Facial action unit (AU) detection is a fundamental block for objective facial expression analysis. Supervised learning approaches require a large amount of manual labeling which is costly. The limited labeled data are also not diverse in terms of gender which can affect model fairness. In this paper, we propose to use synthetically generated data and multi-source domain adaptation (MSDA) to address the problems of the scarcity of labeled data and the diversity of subjects. Specifically, we propose to generate a diverse dataset through synthetic facial expression re-targeting by transferring the expressions from real faces to synthetic avatars. Then, we use MSDA to transfer the AU detection knowledge from a real dataset and the synthetic dataset to a target dataset. Instead of aligning the overall distributions of different domains, we propose Paired Moment Matching (PM2) to align the features of the paired real and synthetic data with the same facial expression. To further improve gender fairness, PM2 matches the features of the real data with a female and a male synthetic image. Our results indicate that synthetic data and the proposed model improve both AU detection performance and fairness across genders, demonstrating its potential to solve AU detection in-the-wild.},
note = {arXiv:2403.10737 [cs]},
keywords = {DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Tran, Minh; Chang, Di; Siniukov, Maksim; Soleymani, Mohammad
Dyadic Interaction Modeling for Social Behavior Generation Miscellaneous
2024, (arXiv:2403.09069 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@misc{tran_dyadic_2024,
title = {Dyadic Interaction Modeling for Social Behavior Generation},
author = {Minh Tran and Di Chang and Maksim Siniukov and Mohammad Soleymani},
url = {http://arxiv.org/abs/2403.09069},
year = {2024},
date = {2024-03-01},
urldate = {2024-03-19},
publisher = {arXiv},
abstract = {Human-human communication is like a delicate dance where listeners and speakers concurrently interact to maintain conversational dynamics. Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction. In this paper, we present an effective framework for creating 3D facial motions in dyadic interactions. Existing work consider a listener as a reactive agent with reflexive behaviors to the speaker's voice and facial motions. The heart of our framework is Dyadic Interaction Modeling (DIM), a pre-training approach that jointly models speakers' and listeners' motions through masking and contrastive learning to learn representations that capture the dyadic context. To enable the generation of non-deterministic behaviors, we encode both listener and speaker motions into discrete latent representations, through VQ-VAE. The pre-trained model is further fine-tuned for motion generation. Extensive experiments demonstrate the superiority of our framework in generating listener motions, establishing a new state-of-the-art according to the quantitative measures capturing the diversity and realism of generated motions. Qualitative results demonstrate the superior capabilities of the proposed approach in generating diverse and realistic expressions, eye blinks and head gestures.},
note = {arXiv:2403.09069 [cs]},
keywords = {DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Kwon, Deuksin; Weiss, Emily; Kulshrestha, Tara; Chawla, Kushal; Lucas, Gale M.; Gratch, Jonathan
Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues Miscellaneous
2024, (arXiv:2402.13550 [cs]).
Abstract | Links | BibTeX | Tags: AI, Virtual Humans
@misc{kwon_are_2024,
title = {Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues},
author = {Deuksin Kwon and Emily Weiss and Tara Kulshrestha and Kushal Chawla and Gale M. Lucas and Jonathan Gratch},
url = {http://arxiv.org/abs/2402.13550},
year = {2024},
date = {2024-02-01},
urldate = {2024-03-14},
publisher = {arXiv},
abstract = {A successful negotiation demands a deep comprehension of the conversation context, Theory-of-Mind (ToM) skills to infer the partner's motives, as well as strategic reasoning and effective communication, making it challenging for automated systems. Given the remarkable performance of LLMs across a variety of NLP tasks, in this work, we aim to understand how LLMs can advance different aspects of negotiation research, ranging from designing dialogue systems to providing pedagogical feedback and scaling up data collection practices. To this end, we devise a methodology to analyze the multifaceted capabilities of LLMs across diverse dialogue scenarios covering all the time stages of a typical negotiation interaction. Our analysis adds to the increasing evidence for the superiority of GPT-4 across various tasks while also providing insights into specific tasks that remain difficult for LLMs. For instance, the models correlate poorly with human players when making subjective assessments about the negotiation dialogues and often struggle to generate responses that are contextually appropriate as well as strategically advantageous.},
note = {arXiv:2402.13550 [cs]},
keywords = {AI, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Marti, Deniz; Hanrahan, David; Sanchez-Triana, Ernesto; Wells, Mona; Corra, Lilian; Hu, Howard; Breysse, Patrick N.; Laborde, Amalia; Caravanos, Jack; Bertollini, Roberto; Porterfield, Kate; Fuller, Richard
Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals Technical Report
Public and Global Health 2024.
Abstract | Links | BibTeX | Tags:
@techreport{marti_structured_2024,
title = {Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals},
author = {Deniz Marti and David Hanrahan and Ernesto Sanchez-Triana and Mona Wells and Lilian Corra and Howard Hu and Patrick N. Breysse and Amalia Laborde and Jack Caravanos and Roberto Bertollini and Kate Porterfield and Richard Fuller},
url = {http://medrxiv.org/lookup/doi/10.1101/2024.01.30.24301863},
doi = {10.1101/2024.01.30.24301863},
year = {2024},
date = {2024-02-01},
urldate = {2024-02-21},
institution = {Public and Global Health},
abstract = {ABSTRACT
Introduction
Chemical contamination and pollution are an ongoing threat to human health and the environment. The concern over the consequences of chemical exposures at the global level continues to grow. Because resources are constrained, there is a need to prioritize interventions focused on the greatest health impact. Data, especially related to chemical exposures, are rarely available for most substances of concern, and alternate methods to evaluate their impact are needed.
Structured Expert Judgment (SEJ) Process
A Structured Expert Judgment
3
process was performed to provide plausible estimates of health impacts for 16 commonly found pollutants: asbestos, arsenic, benzene, chromium, cadmium, dioxins, fluoride, highly hazardous pesticides (HHPs), lead, mercury, polycyclic-aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), Per- and Polyfluorinated Substances (PFAs), phthalates, endocrine disrupting chemicals (EDCs), and brominated flame retardants (BRFs). This process, undertaken by sector experts, weighed individual estimations of the probable global health scale health impacts of each pollutant using objective estimates of the expert opinions’ statistical accuracy and informativeness.
Main Findings
The foremost substances, in terms of mean projected annual total deaths, were lead, asbestos, arsenic, and HHPs. Lead surpasses the others by a large margin, with an estimated median value of 1.7 million deaths annually. The three other substances averaged between 136,000 and 274,000 deaths per year. Of the 12 other chemicals evaluated, none reached an estimated annual death count exceeding 100,000. These findings underscore the importance of prioritizing available resources on reducing and remediating the impacts of these key pollutants.
Range of Health Impacts
Based on the evidence available, experts concluded some of the more notorious chemical pollutants, such as PCBs and dioxin, do not result in high levels of human health impact from a global scale perspective. However, the chemical toxicity of some compounds released in recent decades, such as Endocrine Disrupters and PFAs, cannot be ignored, even if current impacts are limited. Moreover, the impact of some chemicals may be disproportionately large in some geographic areas. Continued research and monitoring are essential; and a preventative approach is needed for chemicals.
Future Directions
These results, and potential similar analyses of other chemicals, are provided as inputs to ongoing discussions about priority setting for global chemicals and pollution management. Furthermore, we suggest that this SEJ process be repeated periodically as new information becomes available.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Introduction
Chemical contamination and pollution are an ongoing threat to human health and the environment. The concern over the consequences of chemical exposures at the global level continues to grow. Because resources are constrained, there is a need to prioritize interventions focused on the greatest health impact. Data, especially related to chemical exposures, are rarely available for most substances of concern, and alternate methods to evaluate their impact are needed.
Structured Expert Judgment (SEJ) Process
A Structured Expert Judgment
3
process was performed to provide plausible estimates of health impacts for 16 commonly found pollutants: asbestos, arsenic, benzene, chromium, cadmium, dioxins, fluoride, highly hazardous pesticides (HHPs), lead, mercury, polycyclic-aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), Per- and Polyfluorinated Substances (PFAs), phthalates, endocrine disrupting chemicals (EDCs), and brominated flame retardants (BRFs). This process, undertaken by sector experts, weighed individual estimations of the probable global health scale health impacts of each pollutant using objective estimates of the expert opinions’ statistical accuracy and informativeness.
Main Findings
The foremost substances, in terms of mean projected annual total deaths, were lead, asbestos, arsenic, and HHPs. Lead surpasses the others by a large margin, with an estimated median value of 1.7 million deaths annually. The three other substances averaged between 136,000 and 274,000 deaths per year. Of the 12 other chemicals evaluated, none reached an estimated annual death count exceeding 100,000. These findings underscore the importance of prioritizing available resources on reducing and remediating the impacts of these key pollutants.
Range of Health Impacts
Based on the evidence available, experts concluded some of the more notorious chemical pollutants, such as PCBs and dioxin, do not result in high levels of human health impact from a global scale perspective. However, the chemical toxicity of some compounds released in recent decades, such as Endocrine Disrupters and PFAs, cannot be ignored, even if current impacts are limited. Moreover, the impact of some chemicals may be disproportionately large in some geographic areas. Continued research and monitoring are essential; and a preventative approach is needed for chemicals.
Future Directions
These results, and potential similar analyses of other chemicals, are provided as inputs to ongoing discussions about priority setting for global chemicals and pollution management. Furthermore, we suggest that this SEJ process be repeated periodically as new information becomes available.
Yu, Zifan; Tavakoli, Erfan Bank; Chen, Meida; You, Suya; Rao, Raghuveer; Agarwal, Sanjeev; Ren, Fengbo
TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection Miscellaneous
2024, (arXiv:2311.02535 [cs]).
Abstract | Links | BibTeX | Tags: Computer Science - Computer Vision and Pattern Recognition, Narrative
@misc{yu_tokenmotion_2024,
title = {TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection},
author = {Zifan Yu and Erfan Bank Tavakoli and Meida Chen and Suya You and Raghuveer Rao and Sanjeev Agarwal and Fengbo Ren},
url = {http://arxiv.org/abs/2311.02535},
year = {2024},
date = {2024-02-01},
urldate = {2024-02-21},
publisher = {arXiv},
abstract = {The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD. It outperforms the existing state-of-the-art method by a 12.8% improvement in weighted F-measure, an 8.4% enhancement in S-measure, and a 10.7% boost in mean IoU. The results demonstrate the benefits of utilizing motion-guided features via learnable token selection within a transformer-based framework to tackle the intricate task of VCOD.},
note = {arXiv:2311.02535 [cs]},
keywords = {Computer Science - Computer Vision and Pattern Recognition, Narrative},
pubstate = {published},
tppubtype = {misc}
}
Saxon, Leslie; Faulk, Robert T; Boberg, Jill; Barrett, Trevor; McLelland, Steve
In: Journal of Special Operations Medicine, 2024, ISSN: 1553-9768.
@article{saxon_continuous_2024,
title = {Continuous Assessment of Active-Duty Army Special Operations and Reconnaissance Marines Using Digital Devices and Custom Software: The Digital Comprehensive Operator Readiness Assessment (DcORA) Study},
author = {Leslie Saxon and Robert T Faulk and Jill Boberg and Trevor Barrett and Steve McLelland},
url = {https://www.jsomonline.org/Citations/PXKK-I23D.php},
doi = {10.55460/PXKK-I23D},
issn = {1553-9768},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-25},
journal = {Journal of Special Operations Medicine},
keywords = {CBC},
pubstate = {published},
tppubtype = {article}
}
Zhang, Hao; Chang, Di; Li, Fang; Soleymani, Mohammad; Ahuja, Narendra
MagicPose4D: Crafting Articulated Models with Appearance and Motion Control Miscellaneous
2024, (Version Number: 1).
Abstract | Links | BibTeX | Tags: Virtual Humans
@misc{zhang_magicpose4d_2024,
title = {MagicPose4D: Crafting Articulated Models with Appearance and Motion Control},
author = {Hao Zhang and Di Chang and Fang Li and Mohammad Soleymani and Narendra Ahuja},
url = {https://arxiv.org/abs/2405.14017},
doi = {10.48550/ARXIV.2405.14017},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-25},
publisher = {arXiv},
abstract = {With the success of 2D and 3D visual generative models, there is growing interest in generating 4D content. Existing methods primarily rely on text prompts to produce 4D content, but they often fall short of accurately defining complex or rare motions. To address this limitation, we propose MagicPose4D, a novel framework for refined control over both appearance and motion in 4D generation. Unlike traditional methods, MagicPose4D accepts monocular videos as motion prompts, enabling precise and customizable motion generation. MagicPose4D comprises two key modules:
i) Dual-Phase 4D Reconstruction Modulevphantom which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase refines the model using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations.
ii) Cross-category Motion Transfer Modulevphantom leverages the predictions from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training.
Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.},
note = {Version Number: 1},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
i) Dual-Phase 4D Reconstruction Modulevphantom which operates in two phases. The first phase focuses on capturing the model's shape using accurate 2D supervision and less accurate but geometrically informative 3D pseudo-supervision without imposing skeleton constraints. The second phase refines the model using more accurate pseudo-3D supervision, obtained in the first phase and introduces kinematic chain-based skeleton constraints to ensure physical plausibility. Additionally, we propose a Global-local Chamfer loss that aligns the overall distribution of predicted mesh vertices with the supervision while maintaining part-level alignment without extra annotations.
ii) Cross-category Motion Transfer Modulevphantom leverages the predictions from the 4D reconstruction module and uses a kinematic-chain-based skeleton to achieve cross-category motion transfer. It ensures smooth transitions between frames through dynamic rigidity, facilitating robust generalization without additional training.
Through extensive experiments, we demonstrate that MagicPose4D significantly improves the accuracy and consistency of 4D content generation, outperforming existing methods in various benchmarks.
Marti, Deniz; Hanrahan, David; Sanchez-Triana, Ernesto; Wells, Mona; Corra, Lilian; Hu, Howard; Breysse, Patrick N.; Laborde, Amalia; Caravanos, Jack; Bertollini, Roberto; Porterfield, Kate; Fuller, Richard
Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals Journal Article
In: medRxiv, pp. 2024.01.30.24301863, 2024.
Abstract | Links | BibTeX | Tags:
@article{marti_structured_2024-1,
title = {Structured Expert Judgement Approach of the Health Impact of Various Chemicals and Classes of Chemicals},
author = {Deniz Marti and David Hanrahan and Ernesto Sanchez-Triana and Mona Wells and Lilian Corra and Howard Hu and Patrick N. Breysse and Amalia Laborde and Jack Caravanos and Roberto Bertollini and Kate Porterfield and Richard Fuller},
url = {http://medrxiv.org/content/early/2024/02/01/2024.01.30.24301863.abstract},
doi = {10.1101/2024.01.30.24301863},
year = {2024},
date = {2024-01-01},
journal = {medRxiv},
pages = {2024.01.30.24301863},
abstract = {Introduction Chemical contamination and pollution are an ongoing threat to human health and the environment. The concern over the consequences of chemical exposures at the global level continues to grow. Because resources are constrained, there is a need to prioritize interventions focused on the greatest health impact. Data, especially related to chemical exposures, are rarely available for most substances of concern, and alternate methods to evaluate their impact are needed.Structured Expert Judgment (SEJ) Process A Structured Expert Judgment3 process was performed to provide plausible estimates of health impacts for 16 commonly found pollutants: asbestos, arsenic, benzene, chromium, cadmium, dioxins, fluoride, highly hazardous pesticides (HHPs), lead, mercury, polycyclic-aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs), Per- and Polyfluorinated Substances (PFAs), phthalates, endocrine disrupting chemicals (EDCs), and brominated flame retardants (BRFs). This process, undertaken by sector experts, weighed individual estimations of the probable global health scale health impacts of each pollutant using objective estimates of the expert opinions’ statistical accuracy and informativeness.Main Findings The foremost substances, in terms of mean projected annual total deaths, were lead, asbestos, arsenic, and HHPs. Lead surpasses the others by a large margin, with an estimated median value of 1.7 million deaths annually. The three other substances averaged between 136,000 and 274,000 deaths per year. Of the 12 other chemicals evaluated, none reached an estimated annual death count exceeding 100,000. These findings underscore the importance of prioritizing available resources on reducing and remediating the impacts of these key pollutants.Range of Health Impacts Based on the evidence available, experts concluded some of the more notorious chemical pollutants, such as PCBs and dioxin, do not result in high levels of human health impact from a global scale perspective. However, the chemical toxicity of some compounds released in recent decades, such as Endocrine Disrupters and PFAs, cannot be ignored, even if current impacts are limited. Moreover, the impact of some chemicals may be disproportionately large in some geographic areas. Continued research and monitoring are essential; and a preventative approach is needed for chemicals.Future Directions These results, and potential similar analyses of other chemicals, are provided as inputs to ongoing discussions about priority setting for global chemicals and pollution management. Furthermore, we suggest that this SEJ process be repeated periodically as new information becomes available.Competing Interest StatementThe authors have declared no competing interest.Funding StatementThe author(s) received no specific funding for this work.Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.YesAll relevant data are within the manuscript and its Supporting Information files.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nye, Benjamin D.; Core, Mark G.; Chereddy, Sai V. R.; Young, Vivian; Auerbach, Daniel
Bootstrapping Assessments for Team Simulations: Transfer Learning Between First-Person-Shooter Game Maps Book Section
In: Sottilare, Robert A.; Schwarz, Jessica (Ed.): Adaptive Instructional Systems, vol. 14727, pp. 261–271, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-60608-3 978-3-031-60609-0, (Series Title: Lecture Notes in Computer Science).
Links | BibTeX | Tags: Learning Sciences, Machine Learning, UARC
@incollection{sottilare_bootstrapping_2024,
title = {Bootstrapping Assessments for Team Simulations: Transfer Learning Between First-Person-Shooter Game Maps},
author = {Benjamin D. Nye and Mark G. Core and Sai V. R. Chereddy and Vivian Young and Daniel Auerbach},
editor = {Robert A. Sottilare and Jessica Schwarz},
url = {https://link.springer.com/10.1007/978-3-031-60609-0_19},
doi = {10.1007/978-3-031-60609-0_19},
isbn = {978-3-031-60608-3 978-3-031-60609-0},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-18},
booktitle = {Adaptive Instructional Systems},
volume = {14727},
pages = {261–271},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {Learning Sciences, Machine Learning, UARC},
pubstate = {published},
tppubtype = {incollection}
}
Core, Mark G.; Nye, Benjamin D.; Fegley, Brent D.
Trend-Aware Scenario Authoring: Adapting Training Toward Patterns from Real Operations Book Section
In: Sottilare, Robert A.; Schwarz, Jessica (Ed.): Adaptive Instructional Systems, vol. 14727, pp. 15–24, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-60608-3 978-3-031-60609-0, (Series Title: Lecture Notes in Computer Science).
Links | BibTeX | Tags: Learning Sciences, UARC
@incollection{sottilare_trend-aware_2024,
title = {Trend-Aware Scenario Authoring: Adapting Training Toward Patterns from Real Operations},
author = {Mark G. Core and Benjamin D. Nye and Brent D. Fegley},
editor = {Robert A. Sottilare and Jessica Schwarz},
url = {https://link.springer.com/10.1007/978-3-031-60609-0_2},
doi = {10.1007/978-3-031-60609-0_2},
isbn = {978-3-031-60608-3 978-3-031-60609-0},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-18},
booktitle = {Adaptive Instructional Systems},
volume = {14727},
pages = {15–24},
publisher = {Springer Nature Switzerland},
address = {Cham},
note = {Series Title: Lecture Notes in Computer Science},
keywords = {Learning Sciences, UARC},
pubstate = {published},
tppubtype = {incollection}
}
Rizzo, Albert Skip; Hartholt, Arno; Mozgai, Sharon
Settling the Score: Virtual Reality as a Tool to Enhance Trauma-Focused Therapy for PTSD Book Section
In: Rich, Grant J.; Kumar, V. K.; Farley, Frank H. (Ed.): Handbook of Media Psychology, pp. 187–213, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-56536-6 978-3-031-56537-3.
@incollection{rich_settling_2024,
title = {Settling the Score: Virtual Reality as a Tool to Enhance Trauma-Focused Therapy for PTSD},
author = {Albert Skip Rizzo and Arno Hartholt and Sharon Mozgai},
editor = {Grant J. Rich and V. K. Kumar and Frank H. Farley},
url = {https://link.springer.com/10.1007/978-3-031-56537-3_14},
doi = {10.1007/978-3-031-56537-3_14},
isbn = {978-3-031-56536-6 978-3-031-56537-3},
year = {2024},
date = {2024-01-01},
urldate = {2024-06-18},
booktitle = {Handbook of Media Psychology},
pages = {187–213},
publisher = {Springer Nature Switzerland},
address = {Cham},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Awada, Mohamad; Seyedrezaei, Mirmahdi; Becerik-Gerber, Burcin; Lucas, Gale
Investigating the Interplay between Indoor Environmental Quality and Workers’ Health and Productivity: Preliminary Results Proceedings Article
In: Computing in Civil Engineering 2023, pp. 614–622, American Society of Civil Engineers, Corvallis, Oregon, 2024, ISBN: 978-0-7844-8524-8.
Links | BibTeX | Tags: Virtual Humans
@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}
}
Liu, Ruying; Becerik-Gerber, Burçin; Lucas, Gale M.; Busta, Kelly
Development of a VR Training Platform for Active Shooter Incident Preparedness in Healthcare Environments via a Stakeholder-Engaged Process Proceedings Article
In: Computing in Civil Engineering 2023, pp. 45–53, American Society of Civil Engineers, Corvallis, Oregon, 2024, ISBN: 978-0-7844-8523-1.
Links | BibTeX | Tags: Virtual Humans, VR
@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}
}
Rodrigues, Patrick B.; Becerik-Gerber, Burcin; Soibelman, Lucio; Lucas, Gale M.; Roll, Shawn C.
Virtual Environment for Studying the Effects of Operational and Environmental Sounds on Teleoperated Demolition Proceedings Article
In: Computing in Civil Engineering 2023, pp. 54–61, American Society of Civil Engineers, Corvallis, Oregon, 2024, ISBN: 978-0-7844-8523-1.
Links | BibTeX | Tags: Virtual Humans, VR
@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 = {Virtual Humans, VR},
pubstate = {published},
tppubtype = {inproceedings}
}
Soleymani, Mohammad; Rahmani, Mehdi; Bigdeli, Nooshin
Robust Tube-Based Reference Tracking Nonlinear Model Predictive Control for Wind Turbines Journal Article
In: IEEE Transactions on Automation Science and Engineering, pp. 1–13, 2024, ISSN: 1545-5955, 1558-3783.
@article{soleymani_robust_2024,
title = {Robust Tube-Based Reference Tracking Nonlinear Model Predictive Control for Wind Turbines},
author = {Mohammad Soleymani and Mehdi Rahmani and Nooshin Bigdeli},
url = {https://ieeexplore.ieee.org/document/10495787/},
doi = {10.1109/TASE.2024.3385714},
issn = {1545-5955, 1558-3783},
year = {2024},
date = {2024-01-01},
urldate = {2024-04-16},
journal = {IEEE Transactions on Automation Science and Engineering},
pages = {1–13},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; Leeds, Andrew; Fast, Ed; Sookiassian, Edwin; Kim, Kevin; Beland, Sarah; Kulkarni, Pranav; Mozgai, Sharon
Multidisciplinary Research & Development of Multi-Agents and Virtual Humans Leveraging Integrated Middleware Platforms Proceedings Article
In: 2024.
Abstract | Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@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}
}
Joshi, Himanshu; Ustun, Volkan
Augmenting Cognitive Architectures with Large Language Models Journal Article
In: Proceedings of the AAAI Symposium Series, vol. 2, no. 1, pp. 281–285, 2024, ISSN: 2994-4317.
Abstract | Links | BibTeX | Tags: Cognitive Architecture
@article{joshi_augmenting_2024,
title = {Augmenting Cognitive Architectures with Large Language Models},
author = {Himanshu Joshi and Volkan Ustun},
url = {https://ojs.aaai.org/index.php/AAAI-SS/article/view/27689},
doi = {10.1609/aaaiss.v2i1.27689},
issn = {2994-4317},
year = {2024},
date = {2024-01-01},
urldate = {2024-04-16},
journal = {Proceedings of the AAAI Symposium Series},
volume = {2},
number = {1},
pages = {281–285},
abstract = {A particular fusion of generative models and cognitive architectures is discussed with the help of the Soar and Sigma cognitive architectures. After a brief introduction to cognitive architecture concepts and Large Language Models as exemplar generative AI models, one approach towards their fusion is discussed. This is then analyzed with a summary of potential benefits and extensions needed to existing cognitive architecture that is closest to the proposal.},
keywords = {Cognitive Architecture},
pubstate = {published},
tppubtype = {article}
}
Liu, Ziming; Suen, Christine Wun Ki; Zou, Zhengbo; Chen, Meida; Shi, Yangming
Assessing Workers’ Operational Postures via Egocentric Camera Mapping Proceedings Article
In: Computing in Civil Engineering 2023, pp. 17–24, American Society of Civil Engineers, Corvallis, Oregon, 2024, ISBN: 978-0-7844-8522-4.
Links | BibTeX | Tags: Narrative, STG
@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}
}
Ustun, Volkan; Jorvekar, Ronit; Gurney, Nikolos; Pynadath, David; Wang, Yunzhe
Assessing Routing Decisions of Search and Rescue Teams in Service of an Artificial Social Intelligence Agent: Proceedings Article
In: Proceedings of the 16th International Conference on Agents and Artificial Intelligence, pp. 313–320, SCITEPRESS - Science and Technology Publications, Rome, Italy, 2024, ISBN: 978-989-758-680-4.
Links | BibTeX | Tags: AI, Cognitive Architecture, Social Simulation
@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 = {2024-01-01},
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}
}
Gurney, Nikolos; Morstatter, Fred; Pynadath, David V.; Russell, Adam; Satyukov, Gleb
Operational Collective Intelligence of Humans and Machines Journal Article
In: 2024, (Publisher: [object Object] Version Number: 1).
Abstract | Links | BibTeX | Tags: DTIC, Social Simulation, UARC
@article{gurney_operational_2024,
title = {Operational Collective Intelligence of Humans and Machines},
author = {Nikolos Gurney and Fred Morstatter and David V. Pynadath and Adam Russell and Gleb Satyukov},
url = {https://arxiv.org/abs/2402.13273},
doi = {10.48550/ARXIV.2402.13273},
year = {2024},
date = {2024-01-01},
urldate = {2024-03-14},
abstract = {We explore the use of aggregative crowdsourced forecasting (ACF) as a mechanism to help operationalize ``collective intelligence'' of human-machine teams for coordinated actions. We adopt the definition for Collective Intelligence as: ``A property of groups that emerges from synergies among data-information-knowledge, software-hardware, and individuals (those with new insights as well as recognized authorities) that enables just-in-time knowledge for better decisions than these three elements acting alone.'' Collective Intelligence emerges from new ways of connecting humans and AI to enable decision-advantage, in part by creating and leveraging additional sources of information that might otherwise not be included. Aggregative crowdsourced forecasting (ACF) is a recent key advancement towards Collective Intelligence wherein predictions (Xtextbackslash% probability that Y will happen) and rationales (why I believe it is this probability that X will happen) are elicited independently from a diverse crowd, aggregated, and then used to inform higher-level decision-making. This research asks whether ACF, as a key way to enable Operational Collective Intelligence, could be brought to bear on operational scenarios (i.e., sequences of events with defined agents, components, and interactions) and decision-making, and considers whether such a capability could provide novel operational capabilities to enable new forms of decision-advantage.},
note = {Publisher: [object Object]
Version Number: 1},
keywords = {DTIC, Social Simulation, UARC},
pubstate = {published},
tppubtype = {article}
}
Gurney, Nikolos; Pynadath, David V.; Ustun, Volkan
Spontaneous Theory of Mind for Artificial Intelligence Journal Article
In: 2024, (Publisher: [object Object] Version Number: 1).
Abstract | Links | BibTeX | Tags: AI, DTIC, Social Simulation, UARC
@article{gurney_spontaneous_2024,
title = {Spontaneous Theory of Mind for Artificial Intelligence},
author = {Nikolos Gurney and David V. Pynadath and Volkan Ustun},
url = {https://arxiv.org/abs/2402.13272},
doi = {10.48550/ARXIV.2402.13272},
year = {2024},
date = {2024-01-01},
urldate = {2024-03-14},
abstract = {Existing approaches to Theory of Mind (ToM) in Artificial Intelligence (AI) overemphasize prompted, or cue-based, ToM, which may limit our collective ability to develop Artificial Social Intelligence (ASI). Drawing from research in computer science, cognitive science, and related disciplines, we contrast prompted ToM with what we call spontaneous ToM – reasoning about others' mental states that is grounded in unintentional, possibly uncontrollable cognitive functions. We argue for a principled approach to studying and developing AI ToM and suggest that a robust, or general, ASI will respond to prompts textbackslashtextitand spontaneously engage in social reasoning.},
note = {Publisher: [object Object]
Version Number: 1},
keywords = {AI, DTIC, Social Simulation, UARC},
pubstate = {published},
tppubtype = {article}
}
Gratch, Jonathan; Greene, Gretchen; Picard, Rosalind; Urquhart, Lachlan; Valstar, Michel
Guest Editorial: Ethics in Affective Computing Journal Article
In: IEEE Transactions on Affective Computing, vol. 15, no. 1, pp. 1–3, 2024, ISSN: 1949-3045, 2371-9850.
Links | BibTeX | Tags: Virtual Humans
@article{gratch_guest_2024,
title = {Guest Editorial: Ethics in Affective Computing},
author = {Jonathan Gratch and Gretchen Greene and Rosalind Picard and Lachlan Urquhart and Michel Valstar},
url = {https://ieeexplore.ieee.org/document/10454111/},
doi = {10.1109/TAFFC.2023.3322918},
issn = {1949-3045, 2371-9850},
year = {2024},
date = {2024-01-01},
urldate = {2024-03-14},
journal = {IEEE Transactions on Affective Computing},
volume = {15},
number = {1},
pages = {1–3},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Spiegel, Brennan M. R.; Rizzo, Albert; Persky, Susan; Liran, Omer; Wiederhold, Brenda; Woods, Susan; Donovan, Kate; Sarkar, Korak; Xiang, Henry; Joo, Sun; Jotwani, Rohan; Lang, Min; Paul, Margot; Senter-Zapata, Mike; Widmeier, Keith; Zhang, Haipeng
What Is Medical Extended Reality? A Taxonomy Defining the Current Breadth and Depth of an Evolving Field Journal Article
In: Journal of Medical Extended Reality, vol. 1, no. 1, pp. 4–12, 2024, ISSN: 2994-1520.
Links | BibTeX | Tags: DTIC, MedVR, UARC
@article{spiegel_what_2024,
title = {What Is Medical Extended Reality? A Taxonomy Defining the Current Breadth and Depth of an Evolving Field},
author = {Brennan M. R. Spiegel and Albert Rizzo and Susan Persky and Omer Liran and Brenda Wiederhold and Susan Woods and Kate Donovan and Korak Sarkar and Henry Xiang and Sun Joo and Rohan Jotwani and Min Lang and Margot Paul and Mike Senter-Zapata and Keith Widmeier and Haipeng Zhang},
url = {https://www.liebertpub.com/doi/10.1089/jmxr.2023.0012},
doi = {10.1089/jmxr.2023.0012},
issn = {2994-1520},
year = {2024},
date = {2024-01-01},
urldate = {2024-02-20},
journal = {Journal of Medical Extended Reality},
volume = {1},
number = {1},
pages = {4–12},
keywords = {DTIC, MedVR, UARC},
pubstate = {published},
tppubtype = {article}
}
Awada, Mohamad; Gerber, Burcin Becerik; Lucas, Gale M.; Roll, Shawn C.
Stress appraisal in the workplace and its associations with productivity and mood: Insights from a multimodal machine learning analysis Journal Article
In: PLOS ONE, vol. 19, no. 1, pp. e0296468, 2024, ISSN: 1932-6203.
Abstract | Links | BibTeX | Tags: DTIC, Machine Learning, UARC
@article{awada_stress_2024,
title = {Stress appraisal in the workplace and its associations with productivity and mood: Insights from a multimodal machine learning analysis},
author = {Mohamad Awada and Burcin Becerik Gerber and Gale M. Lucas and Shawn C. Roll},
editor = {Iftikhar Ahmed Khan},
url = {https://dx.plos.org/10.1371/journal.pone.0296468},
doi = {10.1371/journal.pone.0296468},
issn = {1932-6203},
year = {2024},
date = {2024-01-01},
urldate = {2024-02-21},
journal = {PLOS ONE},
volume = {19},
number = {1},
pages = {e0296468},
abstract = {Previous studies have primarily focused on predicting stress arousal, encompassing physiological, behavioral, and psychological responses to stressors, while neglecting the examination of stress appraisal. Stress appraisal involves the cognitive evaluation of a situation as stressful or non-stressful, and as a threat/pressure or a challenge/opportunity. In this study, we investigated several research questions related to the association between states of stress appraisal (i.e., boredom, eustress, coexisting eustress-distress, distress) and various factors such as stress levels, mood, productivity, physiological and behavioral responses, as well as the most effective ML algorithms and data signals for predicting stress appraisal. The results support the Yerkes-Dodson law, showing that a moderate stress level is associated with increased productivity and positive mood, while low and high levels of stress are related to decreased productivity and negative mood, with distress overpowering eustress when they coexist. Changes in stress appraisal relative to physiological and behavioral features were examined through the lenses of stress arousal, activity engagement, and performance. An XGBOOST model achieved the best prediction accuracies of stress appraisal, reaching 82.78% when combining physiological and behavioral features and 79.55% using only the physiological dataset. The small accuracy difference of 3% indicates that physiological data alone may be adequate to accurately predict stress appraisal, and the feature importance results identified electrodermal activity, skin temperature, and blood volume pulse as the most useful physiologic features. Implementing these models within work environments can serve as a foundation for designing workplace policies, practices, and stress management strategies that prioritize the promotion of eustress while reducing distress and boredom. Such efforts can foster a supportive work environment to enhance employee well-being and productivity.},
keywords = {DTIC, Machine Learning, UARC},
pubstate = {published},
tppubtype = {article}
}
Jago, Arthur S.; Raveendhran, Roshni; Fast, Nathanael; Gratch, Jonathan
Algorithmic management diminishes status: An unintended consequence of using machines to perform social roles Journal Article
In: Journal of Experimental Social Psychology, vol. 110, pp. 104553, 2024, ISSN: 00221031.
Links | BibTeX | Tags: Virtual Humans
@article{jago_algorithmic_2024,
title = {Algorithmic management diminishes status: An unintended consequence of using machines to perform social roles},
author = {Arthur S. Jago and Roshni Raveendhran and Nathanael Fast and Jonathan Gratch},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0022103123001105},
doi = {10.1016/j.jesp.2023.104553},
issn = {00221031},
year = {2024},
date = {2024-01-01},
urldate = {2024-02-21},
journal = {Journal of Experimental Social Psychology},
volume = {110},
pages = {104553},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Shi, Zhonghao; O'Connell, Allison; Li, Zongjian; Liu, Siqi; Ayissi, Jennifer; Hoffman, Guy; Soleymani, Mohammad; Matarić, Maja J.
Build Your Own Robot Friend: An Open-Source Learning Module for Accessible and Engaging AI Education Miscellaneous
2024, (arXiv:2402.01647 [cs]).
Abstract | Links | BibTeX | Tags: Virtual Humans
@misc{shi_build_2024,
title = {Build Your Own Robot Friend: An Open-Source Learning Module for Accessible and Engaging AI Education},
author = {Zhonghao Shi and Allison O'Connell and Zongjian Li and Siqi Liu and Jennifer Ayissi and Guy Hoffman and Mohammad Soleymani and Maja J. Matarić},
url = {http://arxiv.org/abs/2402.01647},
year = {2024},
date = {2024-01-01},
urldate = {2024-02-21},
publisher = {arXiv},
abstract = {As artificial intelligence (AI) is playing an increasingly important role in our society and global economy, AI education and literacy have become necessary components in college and K-12 education to prepare students for an AI-powered society. However, current AI curricula have not yet been made accessible and engaging enough for students and schools from all socio-economic backgrounds with different educational goals. In this work, we developed an open-source learning module for college and high school students, which allows students to build their own robot companion from the ground up. This open platform can be used to provide hands-on experience and introductory knowledge about various aspects of AI, including robotics, machine learning (ML), software engineering, and mechanical engineering. Because of the social and personal nature of a socially assistive robot companion, this module also puts a special emphasis on human-centered AI, enabling students to develop a better understanding of human-AI interaction and AI ethics through hands-on learning activities. With open-source documentation, assembling manuals and affordable materials, students from different socio-economic backgrounds can personalize their learning experience based on their individual educational goals. To evaluate the student-perceived quality of our module, we conducted a usability testing workshop with 15 college students recruited from a minority-serving institution. Our results indicate that our AI module is effective, easy-to-follow, and engaging, and it increases student interest in studying AI/ML and robotics in the future. We hope that this work will contribute toward accessible and engaging AI education in human-AI interaction for college and high school students.},
note = {arXiv:2402.01647 [cs]},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Murawski, Alaine; Ramirez‐Zohfeld, Vanessa; Mell, Johnathan; Tschoe, Marianne; Schierer, Allison; Olvera, Charles; Brett, Jeanne; Gratch, Jonathan; Lindquist, Lee A.
Development and pilot testing of an artificial intelligence‐based family caregiver negotiation program Journal Article
In: Journal of the American Geriatrics Society, pp. jgs.18775, 2024, ISSN: 0002-8614, 1532-5415.
Abstract | Links | BibTeX | Tags: AI, Virtual Humans
@article{murawski_development_2024,
title = {Development and pilot testing of an artificial intelligence‐based family caregiver negotiation program},
author = {Alaine Murawski and Vanessa Ramirez‐Zohfeld and Johnathan Mell and Marianne Tschoe and Allison Schierer and Charles Olvera and Jeanne Brett and Jonathan Gratch and Lee A. Lindquist},
url = {https://agsjournals.onlinelibrary.wiley.com/doi/10.1111/jgs.18775},
doi = {10.1111/jgs.18775},
issn = {0002-8614, 1532-5415},
year = {2024},
date = {2024-01-01},
urldate = {2024-02-21},
journal = {Journal of the American Geriatrics Society},
pages = {jgs.18775},
abstract = {Abstract
Background
Family caregivers of people with Alzheimer's disease experience conflicts as they navigate health care but lack training to resolve these disputes. We sought to develop and pilot test an artificial‐intelligence negotiation training program, NegotiAge, for family caregivers.
Methods
We convened negotiation experts, a geriatrician, a social worker, and community‐based family caregivers. Content matter experts created short videos to teach negotiation skills. Caregivers generated dialogue surrounding conflicts. Computer scientists utilized the dialogue with the Interactive Arbitration Guide Online (IAGO) platform to develop avatar‐based agents (e.g., sibling, older adult, physician) for caregivers to practice negotiating. Pilot testing was conducted with family caregivers to assess usability (USE) and satisfaction (open‐ended questions with thematic analysis).
Results
Development: With NegotiAge, caregivers progress through didactic material, then receive scenarios to negotiate (e.g., physician recommends gastric tube, sibling disagrees with home support, older adult refusing support). Caregivers negotiate in real‐time with avatars who are designed to act like humans, including emotional tactics and irrational behaviors. Caregivers send/receive offers, using tactics until either mutual agreement or time expires. Immediate feedback is generated for the user to improve skills training. Pilot testing: Family caregivers (
n = 12) completed the program and survey. USE questionnaire (Likert scale 1–7) subset scores revealed: (1) Useful—Mean 5.69 (SD 0.76); (2) Ease—Mean 5.24 (SD 0.96); (3) Learn—Mean 5.69 (SD 0.74); (4) Satisfy—Mean 5.62 (SD 1.10). Items that received over 80% agreements were: It helps me be more effective; It helps me be more productive; It is useful; It gives me more control over the activities in my life; It makes the things I want to accomplish easier to get done. Participants were highly satisfied and found NegotiAge fun to use (91.7%), with 100% who would recommend it to a friend.
Conclusion
NegotiAge is an Artificial‐Intelligent Caregiver Negotiation Program, that is usable and feasible for family caregivers to become familiar with negotiating conflicts commonly seen in health care.},
keywords = {AI, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Background
Family caregivers of people with Alzheimer's disease experience conflicts as they navigate health care but lack training to resolve these disputes. We sought to develop and pilot test an artificial‐intelligence negotiation training program, NegotiAge, for family caregivers.
Methods
We convened negotiation experts, a geriatrician, a social worker, and community‐based family caregivers. Content matter experts created short videos to teach negotiation skills. Caregivers generated dialogue surrounding conflicts. Computer scientists utilized the dialogue with the Interactive Arbitration Guide Online (IAGO) platform to develop avatar‐based agents (e.g., sibling, older adult, physician) for caregivers to practice negotiating. Pilot testing was conducted with family caregivers to assess usability (USE) and satisfaction (open‐ended questions with thematic analysis).
Results
Development: With NegotiAge, caregivers progress through didactic material, then receive scenarios to negotiate (e.g., physician recommends gastric tube, sibling disagrees with home support, older adult refusing support). Caregivers negotiate in real‐time with avatars who are designed to act like humans, including emotional tactics and irrational behaviors. Caregivers send/receive offers, using tactics until either mutual agreement or time expires. Immediate feedback is generated for the user to improve skills training. Pilot testing: Family caregivers (
n = 12) completed the program and survey. USE questionnaire (Likert scale 1–7) subset scores revealed: (1) Useful—Mean 5.69 (SD 0.76); (2) Ease—Mean 5.24 (SD 0.96); (3) Learn—Mean 5.69 (SD 0.74); (4) Satisfy—Mean 5.62 (SD 1.10). Items that received over 80% agreements were: It helps me be more effective; It helps me be more productive; It is useful; It gives me more control over the activities in my life; It makes the things I want to accomplish easier to get done. Participants were highly satisfied and found NegotiAge fun to use (91.7%), with 100% who would recommend it to a friend.
Conclusion
NegotiAge is an Artificial‐Intelligent Caregiver Negotiation Program, that is usable and feasible for family caregivers to become familiar with negotiating conflicts commonly seen in health care.
Barrett, Trevor; Faulk, Robert; Sergeant, Army Master; Boberg, Jill; Bartels, Matthew; Colonel, Marine Lieutenant; Saxon, Leslie A.
Force plate assessments in reconnaissance marine training company Journal Article
In: BMC Sports Science, Medicine and Rehabilitation, vol. 16, no. 1, pp. 16, 2024, ISSN: 2052-1847.
Abstract | Links | BibTeX | Tags: DTIC, MedVR, UARC
@article{barrett_force_2024,
title = {Force plate assessments in reconnaissance marine training company},
author = {Trevor Barrett and Robert Faulk and Army Master Sergeant and Jill Boberg and Matthew Bartels and Marine Lieutenant Colonel and Leslie A. Saxon},
url = {https://bmcsportsscimedrehabil.biomedcentral.com/articles/10.1186/s13102-023-00796-z},
doi = {10.1186/s13102-023-00796-z},
issn = {2052-1847},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-22},
journal = {BMC Sports Science, Medicine and Rehabilitation},
volume = {16},
number = {1},
pages = {16},
abstract = {Abstract
The ability to obtain dynamic movement assessments using force plate technology holds the promise of providing more detailed knowledge of the strength, balance and forces generated by active-duty military personnel. To date, there are not well-defined use cases for implementation of force plate assessments in military training environments. We sought to determine if force plate technology assessments could provide additional insights, related to the likelihood of graduation, beyond that provided by traditional physical fitness tests (PFT’s), in an elite Marine training school. Serial force plate measures were also obtained on those Marines successfully completing training to determine if consistent measures reflecting the effects of training on muscle skeletal load-over-time could be accurately measured. A pre-training force plate assessment performed in 112 Marines did not predict graduation rates. For Marines who successfully completed the course, serial measures obtained throughout training were highly variable for each individual and no firm conclusions could be drawn related to load imposed or the fitness attained during training.},
keywords = {DTIC, MedVR, UARC},
pubstate = {published},
tppubtype = {article}
}
The ability to obtain dynamic movement assessments using force plate technology holds the promise of providing more detailed knowledge of the strength, balance and forces generated by active-duty military personnel. To date, there are not well-defined use cases for implementation of force plate assessments in military training environments. We sought to determine if force plate technology assessments could provide additional insights, related to the likelihood of graduation, beyond that provided by traditional physical fitness tests (PFT’s), in an elite Marine training school. Serial force plate measures were also obtained on those Marines successfully completing training to determine if consistent measures reflecting the effects of training on muscle skeletal load-over-time could be accurately measured. A pre-training force plate assessment performed in 112 Marines did not predict graduation rates. For Marines who successfully completed the course, serial measures obtained throughout training were highly variable for each individual and no firm conclusions could be drawn related to load imposed or the fitness attained during training.
2023
Zhou, Emily; Soleymani, Mohammad; Matarić, Maja J.
Investigating the Generalizability of Physiological Characteristics of Anxiety Proceedings Article
In: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 4848–4855, IEEE, Istanbul, Turkiye, 2023, ISBN: 9798350337488.
@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 = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tak, Ala Nekouvaght; Becerik-Gerber, Burçin; Soibelman, Lucio; Lucas, Gale
A framework for investigating the acceptance of smart home technologies: Findings for residential smart HVAC systems Journal Article
In: Building and Environment, vol. 245, pp. 110935, 2023, ISSN: 03601323.
Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@article{tak_framework_2023,
title = {A framework for investigating the acceptance of smart home technologies: Findings for residential smart HVAC systems},
author = {Ala Nekouvaght Tak and Burçin Becerik-Gerber and Lucio Soibelman and Gale Lucas},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0360132323009629},
doi = {10.1016/j.buildenv.2023.110935},
issn = {03601323},
year = {2023},
date = {2023-11-01},
urldate = {2023-12-07},
journal = {Building and Environment},
volume = {245},
pages = {110935},
keywords = {DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Cho, Hyundong; Liu, Shuai; Shi, Taiwei; Jain, Darpan; Rizk, Basem; Huang, Yuyang; Lu, Zixun; Wen, Nuan; Gratch, Jonathan; Ferrara, Emilio; May, Jonathan
Can Language Model Moderators Improve the Health of Online Discourse? Miscellaneous
2023, (arXiv:2311.10781 [cs]).
Abstract | Links | BibTeX | Tags: AI, Dialogue, DTIC, UARC, Virtual Humans
@misc{cho_can_2023,
title = {Can Language Model Moderators Improve the Health of Online Discourse?},
author = {Hyundong Cho and Shuai Liu and Taiwei Shi and Darpan Jain and Basem Rizk and Yuyang Huang and Zixun Lu and Nuan Wen and Jonathan Gratch and Emilio Ferrara and Jonathan May},
url = {http://arxiv.org/abs/2311.10781},
year = {2023},
date = {2023-11-01},
urldate = {2023-12-07},
publisher = {arXiv},
abstract = {Human moderation of online conversation is essential to maintaining civility and focus in a dialogue, but is challenging to scale and harmful to moderators. The inclusion of sophisticated natural language generation modules as a force multiplier aid moderators is a tantalizing prospect, but adequate evaluation approaches have so far been elusive. In this paper, we establish a systematic definition of conversational moderation effectiveness through a multidisciplinary lens that incorporates insights from social science. We then propose a comprehensive evaluation framework that uses this definition to asses models' moderation capabilities independently of human intervention. With our framework, we conduct the first known study of conversational dialogue models as moderators, finding that appropriately prompted models can provide specific and fair feedback on toxic behavior but struggle to influence users to increase their levels of respect and cooperation.},
note = {arXiv:2311.10781 [cs]},
keywords = {AI, Dialogue, DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Yang, Daniel; Kommineni, Aditya; Alshehri, Mohammad; Mohanty, Nilamadhab; Modi, Vedant; Gratch, Jonathan; Narayanan, Shrikanth
Context Unlocks Emotions: Text-based Emotion Classification Dataset Auditing with Large Language Models Miscellaneous
2023, (arXiv:2311.03551 [cs]).
Abstract | Links | BibTeX | Tags: AI, DTIC, UARC, Virtual Humans
@misc{yang_context_2023,
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 = {http://arxiv.org/abs/2311.03551},
year = {2023},
date = {2023-11-01},
urldate = {2023-12-07},
publisher = {arXiv},
abstract = {The lack of contextual information in text data can make the annotation process of text-based emotion classification datasets challenging. As a result, such datasets often contain labels that fail to consider all the relevant emotions in the vocabulary. This misalignment between text inputs and labels can degrade the performance of machine learning models trained on top of them. As re-annotating entire datasets is a costly and time-consuming task that cannot be done at scale, we propose to use the expressive capabilities of large language models to synthesize additional context for input text to increase its alignment with the annotated emotional labels. In this work, we propose a formal definition of textual context to motivate a prompting strategy to enhance such contextual information. We provide both human and empirical evaluation to demonstrate the efficacy of the enhanced context. Our method improves alignment between inputs and their human-annotated labels from both an empirical and human-evaluated standpoint.},
note = {arXiv:2311.03551 [cs]},
keywords = {AI, DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Chang, Di; Shi, Yichun; Gao, Quankai; Fu, Jessica; Xu, Hongyi; Song, Guoxian; Yan, Qing; Yang, Xiao; Soleymani, Mohammad
MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer Miscellaneous
2023, (arXiv:2311.12052 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@misc{chang_magicdance_2023,
title = {MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer},
author = {Di Chang and Yichun Shi and Quankai Gao and Jessica Fu and Hongyi Xu and Guoxian Song and Qing Yan and Xiao Yang and Mohammad Soleymani},
url = {http://arxiv.org/abs/2311.12052},
year = {2023},
date = {2023-11-01},
urldate = {2023-12-07},
publisher = {arXiv},
abstract = {In this work, we propose MagicDance, a diffusion-based model for 2D human motion and facial expression transfer on challenging human dance videos. Specifically, we aim to generate human dance videos of any target identity driven by novel pose sequences while keeping the identity unchanged. To this end, we propose a two-stage training strategy to disentangle human motions and appearance (e.g., facial expressions, skin tone and dressing), consisting of the pretraining of an appearance-control block and fine-tuning of an appearance-pose-joint-control block over human dance poses of the same dataset. Our novel design enables robust appearance control with temporally consistent upper body, facial attributes, and even background. The model also generalizes well on unseen human identities and complex motion sequences without the need for any fine-tuning with additional data with diverse human attributes by leveraging the prior knowledge of image diffusion models. Moreover, the proposed model is easy to use and can be considered as a plug-in module/extension to Stable Diffusion. We also demonstrate the model's ability for zero-shot 2D animation generation, enabling not only the appearance transfer from one identity to another but also allowing for cartoon-like stylization given only pose inputs. Extensive experiments demonstrate our superior performance on the TikTok dataset.},
note = {arXiv:2311.12052 [cs]},
keywords = {DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {misc}
}
Liu, Ruying; Awada, Mohamad; Gerber, Burcin Becerik; Lucas, Gale M.; Roll, Shawn C.
Gender moderates the effects of ambient bergamot scent on stress restoration in offices Journal Article
In: Journal of Environmental Psychology, vol. 91, pp. 102135, 2023, ISSN: 02724944.
Links | BibTeX | Tags: DTIC, UARC, Virtual Humans
@article{liu_gender_2023,
title = {Gender moderates the effects of ambient bergamot scent on stress restoration in offices},
author = {Ruying Liu and Mohamad Awada and Burcin Becerik Gerber and Gale M. Lucas and Shawn C. Roll},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0272494423001834},
doi = {10.1016/j.jenvp.2023.102135},
issn = {02724944},
year = {2023},
date = {2023-11-01},
urldate = {2023-09-20},
journal = {Journal of Environmental Psychology},
volume = {91},
pages = {102135},
keywords = {DTIC, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Liu, Rong; Zhao, Enyu; Liu, Zhiyuan; Feng, Andrew; Easley, Scott John
Instant Photorealistic Style Transfer: A Lightweight and Adaptive Approach Miscellaneous
2023, (arXiv:2309.10011 [cs, eess]).
Abstract | Links | BibTeX | Tags: DTIC, UARC
@misc{liu_instant_2023,
title = {Instant Photorealistic Style Transfer: A Lightweight and Adaptive Approach},
author = {Rong Liu and Enyu Zhao and Zhiyuan Liu and Andrew Feng and Scott John Easley},
url = {http://arxiv.org/abs/2309.10011},
year = {2023},
date = {2023-10-01},
urldate = {2024-05-14},
publisher = {arXiv},
abstract = {In this paper, we propose an Instant Photorealistic Style Transfer (IPST) approach, designed to achieve instant photorealistic style transfer on super-resolution inputs without the need for pre-training on pair-wise datasets or imposing extra constraints. Our method utilizes a lightweight StyleNet to enable style transfer from a style image to a content image while preserving non-color information. To further enhance the style transfer process, we introduce an instance-adaptive optimization to prioritize the photorealism of outputs and accelerate the convergence of the style network, leading to a rapid training completion within seconds. Moreover, IPST is well-suited for multi-frame style transfer tasks, as it retains temporal and multi-view consistency of the multi-frame inputs such as video and Neural Radiance Field (NeRF). Experimental results demonstrate that IPST requires less GPU memory usage, offers faster multi-frame transfer speed, and generates photorealistic outputs, making it a promising solution for various photorealistic transfer applications.},
note = {arXiv:2309.10011 [cs, eess]},
keywords = {DTIC, UARC},
pubstate = {published},
tppubtype = {misc}
}
Lukin, Stephanie M.; Pollard, Kimberly A.; Bonial, Claire; Hudson, Taylor; Arstein, Ron; Voss, Clare; Traum, David
Navigating to Success in Multi-Modal Human-Robot Collaboration: Analysis and Corpus Release Miscellaneous
2023, (arXiv:2310.17568 [cs]).
Abstract | Links | BibTeX | Tags: DTIC, Natural Language, UARC
@misc{lukin_navigating_2023,
title = {Navigating to Success in Multi-Modal Human-Robot Collaboration: Analysis and Corpus Release},
author = {Stephanie M. Lukin and Kimberly A. Pollard and Claire Bonial and Taylor Hudson and Ron Arstein and Clare Voss and David Traum},
url = {http://arxiv.org/abs/2310.17568},
year = {2023},
date = {2023-10-01},
urldate = {2023-12-07},
publisher = {arXiv},
abstract = {Human-guided robotic exploration is a useful approach to gathering information at remote locations, especially those that might be too risky, inhospitable, or inaccessible for humans. Maintaining common ground between the remotely-located partners is a challenge, one that can be facilitated by multi-modal communication. In this paper, we explore how participants utilized multiple modalities to investigate a remote location with the help of a robotic partner. Participants issued spoken natural language instructions and received from the robot: text-based feedback, continuous 2D LIDAR mapping, and upon-request static photographs. We noticed that different strategies were adopted in terms of use of the modalities, and hypothesize that these differences may be correlated with success at several exploration sub-tasks. We found that requesting photos may have improved the identification and counting of some key entities (doorways in particular) and that this strategy did not hinder the amount of overall area exploration. Future work with larger samples may reveal the effects of more nuanced photo and dialogue strategies, which can inform the training of robotic agents. Additionally, we announce the release of our unique multi-modal corpus of human-robot communication in an exploration context: SCOUT, the Situated Corpus on Understanding Transactions.},
note = {arXiv:2310.17568 [cs]},
keywords = {DTIC, Natural Language, UARC},
pubstate = {published},
tppubtype = {misc}
}
Gilani, Setareh Nasihati; Pollard, Kimberly; Traum, David
Multimodal Prediction of User's Performance in High-Stress Dialogue Interactions Proceedings Article
In: International Cconference on Multimodal Interaction, pp. 71–75, ACM, Paris France, 2023, ISBN: 9798400703218.
Links | BibTeX | Tags: DTIC, Natural Language, UARC
@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}
}