Publications
Search
1.
Liu, Ruying; Becerik-Gerber, Burcin; Lucas, Gale M.
In: International Journal of Human–Computer Interaction, pp. 1–20, 2026, ISSN: 1044-7318, 1532-7590.
@article{liu_technology_2026,
title = {Technology Acceptance in High-Stakes Serious Games: Extending Technology Acceptance Model (TAM) with Affective and Experiential Predictors in Active Shooter Preparedness},
author = {Ruying Liu and Burcin Becerik-Gerber and Gale M. Lucas},
url = {https://www.tandfonline.com/doi/full/10.1080/10447318.2026.2635682},
doi = {10.1080/10447318.2026.2635682},
issn = {1044-7318, 1532-7590},
year = {2026},
date = {2026-03-01},
urldate = {2026-06-18},
journal = {International Journal of Human–Computer Interaction},
pages = {1–20},
abstract = {Active shooter incidents (ASIs) represent extreme threats to public safety. Virtual reality (VR) serious games offer promising training potential, but user acceptance in high-stakes and emotionally intense contexts is underexplored. This study extends the Technology Acceptance Model (TAM) by incorporating affective (perceived enjoyment) and experiential (self-reported engagement) factors. Using a desktop-based VR ASI preparedness simulation with 50 healthcare workers, we tested the extended TAM model. Core TAM relationships hold for ease of use and usefulness, but enjoyment and engagement play distinct roles. Enjoyment strongly predicted adoption, fully mediating the effect of ease of use and partially mediating usefulness. It was associated with high-arousal positive emotions(e.g., inspiration, pride, enthusiasm), reflecting eudaimonic states rather than hedonic fun. Engagement also significantly promoted adoption, though with weaker mediation effects. These findings extend TAM to high-stakes serious games and suggest that effective design should cultivate meaningful enjoyment and engagement without undermining scenario seriousness.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Active shooter incidents (ASIs) represent extreme threats to public safety. Virtual reality (VR) serious games offer promising training potential, but user acceptance in high-stakes and emotionally intense contexts is underexplored. This study extends the Technology Acceptance Model (TAM) by incorporating affective (perceived enjoyment) and experiential (self-reported engagement) factors. Using a desktop-based VR ASI preparedness simulation with 50 healthcare workers, we tested the extended TAM model. Core TAM relationships hold for ease of use and usefulness, but enjoyment and engagement play distinct roles. Enjoyment strongly predicted adoption, fully mediating the effect of ease of use and partially mediating usefulness. It was associated with high-arousal positive emotions(e.g., inspiration, pride, enthusiasm), reflecting eudaimonic states rather than hedonic fun. Engagement also significantly promoted adoption, though with weaker mediation effects. These findings extend TAM to high-stakes serious games and suggest that effective design should cultivate meaningful enjoyment and engagement without undermining scenario seriousness.
2.
Tran, Minh; Siniukov, Maksim; Jin, Zhangyu; Soleymani, Mohammad
Discrete Facial Encoding: A Framework for the Data-driven Facial Display Discovery Proceedings Article
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2348–2358, 2026.
@inproceedings{tran_discrete_2026,
title = {Discrete Facial Encoding: A Framework for the Data-driven Facial Display Discovery},
author = {Minh Tran and Maksim Siniukov and Zhangyu Jin and Mohammad Soleymani},
year = {2026},
date = {2026-03-01},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {2348–2358},
abstract = {Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work,
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work,
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.
Filter
2026
Liu, Ruying; Becerik-Gerber, Burcin; Lucas, Gale M.
In: International Journal of Human–Computer Interaction, pp. 1–20, 2026, ISSN: 1044-7318, 1532-7590.
Abstract | Links | BibTeX | Tags: ARO, DTIC?, VR
@article{liu_technology_2026,
title = {Technology Acceptance in High-Stakes Serious Games: Extending Technology Acceptance Model (TAM) with Affective and Experiential Predictors in Active Shooter Preparedness},
author = {Ruying Liu and Burcin Becerik-Gerber and Gale M. Lucas},
url = {https://www.tandfonline.com/doi/full/10.1080/10447318.2026.2635682},
doi = {10.1080/10447318.2026.2635682},
issn = {1044-7318, 1532-7590},
year = {2026},
date = {2026-03-01},
urldate = {2026-06-18},
journal = {International Journal of Human–Computer Interaction},
pages = {1–20},
abstract = {Active shooter incidents (ASIs) represent extreme threats to public safety. Virtual reality (VR) serious games offer promising training potential, but user acceptance in high-stakes and emotionally intense contexts is underexplored. This study extends the Technology Acceptance Model (TAM) by incorporating affective (perceived enjoyment) and experiential (self-reported engagement) factors. Using a desktop-based VR ASI preparedness simulation with 50 healthcare workers, we tested the extended TAM model. Core TAM relationships hold for ease of use and usefulness, but enjoyment and engagement play distinct roles. Enjoyment strongly predicted adoption, fully mediating the effect of ease of use and partially mediating usefulness. It was associated with high-arousal positive emotions(e.g., inspiration, pride, enthusiasm), reflecting eudaimonic states rather than hedonic fun. Engagement also significantly promoted adoption, though with weaker mediation effects. These findings extend TAM to high-stakes serious games and suggest that effective design should cultivate meaningful enjoyment and engagement without undermining scenario seriousness.},
keywords = {ARO, DTIC?, VR},
pubstate = {published},
tppubtype = {article}
}
Active shooter incidents (ASIs) represent extreme threats to public safety. Virtual reality (VR) serious games offer promising training potential, but user acceptance in high-stakes and emotionally intense contexts is underexplored. This study extends the Technology Acceptance Model (TAM) by incorporating affective (perceived enjoyment) and experiential (self-reported engagement) factors. Using a desktop-based VR ASI preparedness simulation with 50 healthcare workers, we tested the extended TAM model. Core TAM relationships hold for ease of use and usefulness, but enjoyment and engagement play distinct roles. Enjoyment strongly predicted adoption, fully mediating the effect of ease of use and partially mediating usefulness. It was associated with high-arousal positive emotions(e.g., inspiration, pride, enthusiasm), reflecting eudaimonic states rather than hedonic fun. Engagement also significantly promoted adoption, though with weaker mediation effects. These findings extend TAM to high-stakes serious games and suggest that effective design should cultivate meaningful enjoyment and engagement without undermining scenario seriousness.
Tran, Minh; Siniukov, Maksim; Jin, Zhangyu; Soleymani, Mohammad
Discrete Facial Encoding: A Framework for the Data-driven Facial Display Discovery Proceedings Article
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2348–2358, 2026.
Abstract | BibTeX | Tags: ARO, DTIC?, Virtual Humans
@inproceedings{tran_discrete_2026,
title = {Discrete Facial Encoding: A Framework for the Data-driven Facial Display Discovery},
author = {Minh Tran and Maksim Siniukov and Zhangyu Jin and Mohammad Soleymani},
year = {2026},
date = {2026-03-01},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {2348–2358},
abstract = {Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work,
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.},
keywords = {ARO, DTIC?, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work,
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.
we introduce Discrete Facial Encoding (DFE), an unsupervised, data-driven alternative of compact and interpretable dictionary of facial expressions from 3D mesh sequences learned through a Residual Vector Quantized Variational Autoencoder (RVQ-VAE). Our approach first extracts identityinvariant expression features from images using a 3D Morphable Model (3DMM), effectively disentangling factors such as head pose and facial geometry. We then encode these features using an RVQ-VAE, producing a sequence of discrete tokens from a shared codebook, where each token captures a specific, reusable facial deformation patter that contributes to the overall expression. Through extensive experiments, we demonstrate that Discrete Facial Encoding captures more precise facial behaviors than FACS
and other facial encoding alternatives. We evaluate the
utility of our representation across three high-level psychological tasks: stress detection, personality prediction, and depression detection. Using a simple Bag-of-Words model built on top of the learned tokens, our system consistently outperforms both FACS-based pipelines and strong image and video representation learning models such as Masked Autoencoders. Further analysis reveals that our representation covers a wider variety of facial displays, highlighting its potential as a scalable and effective alternative to FACS for psychological and affective computing applications. We released the source code and model weights at https://github.com/ihp-lab/vqface.