Publications
Search
Gandhe, Sudeep; Traum, David
A Semi-automated Evaluation Metric for Dialogue Model Coherence Book Section
In: Situated Dialog in Speech-Based Human-Computer Interaction, pp. 217–225, Springer International Publishing, Cham, 2016, ISBN: 978-3-319-21833-5 978-3-319-21834-2.
@incollection{gandhe_semi-automated_2016,
title = {A Semi-automated Evaluation Metric for Dialogue Model Coherence},
author = {Sudeep Gandhe and David Traum},
url = {http://link.springer.com/10.1007/978-3-319-21834-2_19},
isbn = {978-3-319-21833-5 978-3-319-21834-2},
year = {2016},
date = {2016-04-01},
booktitle = {Situated Dialog in Speech-Based Human-Computer Interaction},
pages = {217–225},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {We propose a new metric, Voted Appropriateness, which can be used to automatically evaluate dialogue policy decisions, once some wizard data has been collected. We show that this metric outperforms a previously proposed metric Weak agreement.We also present a taxonomy for dialogue model evaluation schemas, and orient our new metric within this taxonomy.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Phan, Thai; Krum, David M.; Bolas, Mark
ShodanVR: Immersive Visualization of Text Records from the Shodan Database Proceedings Article
In: Proceedings of the 2016 Workshop on Immersive Analytics (IA), IEEE, Greenville,SC, 2016, ISBN: 978-1-5090-0834-6.
@inproceedings{phan_shodanvr_2016,
title = {ShodanVR: Immersive Visualization of Text Records from the Shodan Database},
author = {Thai Phan and David M. Krum and Mark Bolas},
url = {http://ieeexplore.ieee.org/document/7932379/?part=1},
doi = {10.1109/IMMERSIVE.2016.7932379},
isbn = {978-1-5090-0834-6},
year = {2016},
date = {2016-03-01},
booktitle = {Proceedings of the 2016 Workshop on Immersive Analytics (IA)},
publisher = {IEEE},
address = {Greenville,SC},
abstract = {ShodanVR is an immersive visualization for querying and displaying text records from the Shodan database of Internet connected devices. Shodan provides port connection data retrieved from servers, routers, and other networked devices [2]. Cybersecurity professionals can glean this data for device populations, software versions, and potential security vulnerabilities [1].},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Azmandian, Mahdi; Grechkin, Timofey; Bolas, Mark; Suma, Evan
Automated Path Prediction for Redirected Walking Using Navigation Meshes Proceedings Article
In: 2016 IEEE Symposium on 3D User Interfaces (3DUI), pp. 63–66, IEEE, Greenville, SC, 2016.
@inproceedings{azmandian_automated_2016,
title = {Automated Path Prediction for Redirected Walking Using Navigation Meshes},
author = {Mahdi Azmandian and Timofey Grechkin and Mark Bolas and Evan Suma},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7460032},
doi = {10.1109/3DUI.2016.7460032},
year = {2016},
date = {2016-03-01},
booktitle = {2016 IEEE Symposium on 3D User Interfaces (3DUI)},
pages = {63–66},
publisher = {IEEE},
address = {Greenville, SC},
abstract = {Redirected walking techniques have been introduced to overcome physical space limitations for natural locomotion in virtual reality. These techniques decouple real and virtual user trajectories by subtly steering the user away from the boundaries of the physical space while maintaining the illusion that the user follows the intended virtual path. Effectiveness of redirection algorithms can significantly improve when a reliable prediction of the users future virtual path is available. In current solutions, the future user trajectory is predicted based on non-standardized manual annotations of the environment structure, which is both tedious and inflexible. We propose a method for automatically generating environment annotation graphs and predicting the user trajectory using navigation meshes. We discuss the integration of this method with existing redirected walking algorithms such as FORCE and MPCRed. Automated annotation of the virtual environments structure enables simplified deployment of these algorithms in any virtual environment.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Ning; Pynadath, David V.; Hill, Susan G.
Trust Calibration within a Human-Robot Team: Comparing Automatically Generated Explanations Proceedings Article
In: 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 109–116, IEEE, New Zealand, 2016.
@inproceedings{wang_trust_2016,
title = {Trust Calibration within a Human-Robot Team: Comparing Automatically Generated Explanations},
author = {Ning Wang and David V. Pynadath and Susan G. Hill},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7451741},
doi = {10.1109/HRI.2016.7451741},
year = {2016},
date = {2016-03-01},
booktitle = {2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)},
pages = {109–116},
publisher = {IEEE},
address = {New Zealand},
abstract = {Trust is a critical factor for achieving the full potential of human-robot teams. Researchers have theorized that people will more accurately trust an autonomous system, such as a robot, if they have a more accurate understanding of its decision-making process. Studies have shown that hand-crafted explanations can help maintain trust when the system is less than 100% reliable. In this work, we leverage existing agent algorithms to provide a domain-independent mechanism for robots to automatically generate such explanations. To measure the explanation mechanism's impact on trust, we collected self-reported survey data and behavioral data in an agent-based online testbed that simulates a human-robot team task. The results demonstrate that the added explanation capability led to improvement in transparency, trust, and team performance. Furthermore, by observing the different outcomes due to variations in the robot's explanation content, we gain valuable insight that can help lead to refinement of explanation algorithms to further improve human-robot trust calibration.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hutton, Courtney; Suma, Evan
A Realistic Walking Model for Enhancing Redirection in Virtual Reality Proceedings Article
In: 2016 IEEE Virtual Reality (VR), pp. 183–184, IEEE, Greenville, SC, 2016.
@inproceedings{hutton_realistic_2016,
title = {A Realistic Walking Model for Enhancing Redirection in Virtual Reality},
author = {Courtney Hutton and Evan Suma},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7504714},
doi = {10.1109/VR.2016.7504714},
year = {2016},
date = {2016-03-01},
booktitle = {2016 IEEE Virtual Reality (VR)},
pages = {183–184},
publisher = {IEEE},
address = {Greenville, SC},
abstract = {Redirected walking algorithms require the prediction of human motion in order to effectively steer users away from the boundaries of the physical space. While a virtual walking trajectory may be represented using straight lines connecting waypoints of interest, this simple model does not accurately represent typical user behavior. In this poster we present a more realistic walking model for use in real-time virtual environments that employ redirection techniques. We implemented the model within a framework that can be used for simulation of redirected walking within different virtual and physical environments. Such simulations are useful for the evaluation of redirected walking algorithms and the tuning of parameters under varying conditions. Additionally, the model can also be used to animate an artificial humanoid “ghost walker” to provide a visual demonstration of redirected walking in virtual reality.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Krum, David M.; Kang, Sin-Hwa; Phan, Thai; Dukes, Lauren Cairco; Bolas, Mark
Head Mounted Projection for Enhanced Gaze in Social Interactions Proceedings Article
In: 2016 IEEE Virtual Reality (VR), pp. 209–210, IEEE, Greenville, SC, 2016.
@inproceedings{krum_head_2016,
title = {Head Mounted Projection for Enhanced Gaze in Social Interactions},
author = {David M. Krum and Sin-Hwa Kang and Thai Phan and Lauren Cairco Dukes and Mark Bolas},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7504727},
doi = {10.1109/VR.2016.7504727},
year = {2016},
date = {2016-03-01},
booktitle = {2016 IEEE Virtual Reality (VR)},
pages = {209–210},
publisher = {IEEE},
address = {Greenville, SC},
abstract = {Projected displays can present life-sized imagery of a virtual human character that can be seen by multiple observers. However, typical projected displays can only render that virtual human from a single viewpoint, regardless of whether head tracking is employed. This results in the virtual human being rendered from an incorrect perspective for most individuals. This could cause perceptual miscues, such as the “Mona Lisa” effect, causing the virtual human to appear as if it is simultaneously gazing and pointing at all observers regardless of their location. This may be detrimental to training scenarios in which all trainees must accurately assess where the virtual human is looking or pointing a weapon. We discuss our investigations into the presentation of eye gaze using REFLCT, a previously introduced head mounted projective display. REFLCT uses head tracked, head mounted projectors and retroreflective screens to present personalized, perspective correct imagery to multiple users without the occlusion of a traditional head mounted display. We examined how head mounted projection for enhanced presentation of eye gaze might facilitate or otherwise affect social interactions during a multi-person guessing game of “Twenty Questions.”},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nilsson, Niels; Suma, Evan; Nordahl, Rolf; Bolas, Mark; Serafin, Stefania
Estimation of Detection Thresholds for Audiovisual Rotation Gains Proceedings Article
In: IEEE Virtual Reality 2016, pp. ID: A22, IEEE, Greenville, SC, 2016.
@inproceedings{nilsson_estimation_2016,
title = {Estimation of Detection Thresholds for Audiovisual Rotation Gains},
author = {Niels Nilsson and Evan Suma and Rolf Nordahl and Mark Bolas and Stefania Serafin},
url = {http://ieeevr.org/2016/posters/},
year = {2016},
date = {2016-03-01},
booktitle = {IEEE Virtual Reality 2016},
pages = {ID: A22},
publisher = {IEEE},
address = {Greenville, SC},
abstract = {Redirection techniques allow users to explore large virtual environments on foot while remaining within a limited physical space. However, research has primarily focused on redirection through manipulation of visual stimuli. We describe a within-subjects study (n=31) exploring if participants’ ability to detect differences between real and virtual rotations is influenced by the addition of sound that is spatially aligned with its virtual source. The results revealed similar detection thresholds for conditions involving moving audio, static audio, and no audio. This may be viewed as an indication of visual dominance during scenarios such as the one used for the current study.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Artstein, Ron; Silver, Kenneth
Ethics for a Combined Human-Machine Dialogue Agent Proceedings Article
In: Ethical and Moral Considerations in Non-Human Agents: Papers from the AAAI Spring Symposium, pp. 184–189, AAAI Press, Stanford, California, 2016.
@inproceedings{artstein_ethics_2016,
title = {Ethics for a Combined Human-Machine Dialogue Agent},
author = {Ron Artstein and Kenneth Silver},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS16/paper/viewFile/12706/11948},
year = {2016},
date = {2016-03-01},
booktitle = {Ethical and Moral Considerations in Non-Human Agents: Papers from the AAAI Spring Symposium},
pages = {184–189},
publisher = {AAAI Press},
address = {Stanford, California},
abstract = {We discuss philosophical and ethical issues that arise from a dialogue system intended to portray a real person, using recordings of the person together with a machine agent that selects recordings during a synchronous conversation with a user. System output may count as actions of the speaker if the speaker intends to communicate with users and the outputs represent what the speaker would have chosen to say in context; in such cases the system can justifiably be said to be holding a conversation that is offset in time. The autonomous agent may at times misrepresent the speaker’s intentions, and such failures are analogous to good-faith misunderstandings. The user may or may not need to be informed that the speaker is not organically present, depending on the application.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Azmandian, Mahdi; Grechkin, Timofey; Bolas, Mark; Suma, Evan
The Redirected Walking Toolkit: A Unified Development Platform for Exploring Large Virtual Environments Proceedings Article
In: 2nd Workshop on Everyday Virtual Reality, IEEE, Greenville, SC, 2016.
@inproceedings{azmandian_redirected_2016,
title = {The Redirected Walking Toolkit: A Unified Development Platform for Exploring Large Virtual Environments},
author = {Mahdi Azmandian and Timofey Grechkin and Mark Bolas and Evan Suma},
url = {http://www.adalsimeone.me/papers/WEVR2016/WEVR2016_Azmandian.pdf},
year = {2016},
date = {2016-03-01},
booktitle = {2nd Workshop on Everyday Virtual Reality},
publisher = {IEEE},
address = {Greenville, SC},
abstract = {With the imminent emergence of low-cost tracking solutions, everyday VR users will soon experience the enhanced immersion of natural walking. Even with consumer-grade room-scale tracking, exploring large virtual environments can be made possible using a software solution known as redirected walking. Wide adoption of this technique has been hindered by the complexity and subtleties involved in successfully deploying redirection. To address this matter, we introduce the Redirected Walking Toolkit, to serve as a unified platform for developing, benchmarking, and deploying redirected walking algorithms. Our design enables seamless integration with standard virtual reality configurations, requiring minimal setup effort for content developers.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Roemmele, Melissa; Morgens, Soja-Marie; Gordon, Andrew S.; Morency, Louis-Philippe
Recognizing Human Actions in the Motion Trajectories of Shapes Proceedings Article
In: Proceedings of ACM Intelligent User Interfaces, pp. 271–281, ACM Press, Sonoma, CA, 2016, ISBN: 978-1-4503-4137-0.
@inproceedings{roemmele_recognizing_2016,
title = {Recognizing Human Actions in the Motion Trajectories of Shapes},
author = {Melissa Roemmele and Soja-Marie Morgens and Andrew S. Gordon and Louis-Philippe Morency},
url = {http://dl.acm.org/citation.cfm?id=2856793},
doi = {10.1145/2856767.2856793},
isbn = {978-1-4503-4137-0},
year = {2016},
date = {2016-03-01},
booktitle = {Proceedings of ACM Intelligent User Interfaces},
pages = {271–281},
publisher = {ACM Press},
address = {Sonoma, CA},
abstract = {People naturally anthropomorphize the movement of nonliving objects, as social psychologists Fritz Heider and Marianne Simmel demonstrated in their influential 1944 research study. When they asked participants to narrate an animated film of two triangles and a circle moving in and around a box, participants described the shapes' movement in terms of human actions. Using a framework for authoring and annotating animations in the style of Heider and Simmel, we established new crowdsourced datasets where the motion trajectories of animated shapes are labeled according to the actions they depict. We applied two machine learning approaches, a spatial-temporal bag-of-words model and a recurrent neural network, to the task of automatically recognizing actions in these datasets. Our best results outperformed a majority baseline and showed similarity to human performance, which encourages further use of these datasets for modeling perception from motion trajectories. Future progress on simulating human-like motion perception will require models that integrate motion information with top-down contextual knowledge.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Georgila, Kallirroi; Pynadath, David V.
Towards a Computational Model of Human Opinion Dynamics in Response to Real-World Events Proceedings Article
In: Proceedings of The 29th International FLAIRS Conference, pp. 44–49, AAAI Press, Key Largo, FL, 2016.
@inproceedings{georgila_towards_2016,
title = {Towards a Computational Model of Human Opinion Dynamics in Response to Real-World Events},
author = {Kallirroi Georgila and David V. Pynadath},
url = {http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS16/paper/view/12960/12539},
year = {2016},
date = {2016-03-01},
booktitle = {Proceedings of The 29th International FLAIRS Conference},
pages = {44–49},
publisher = {AAAI Press},
address = {Key Largo, FL},
abstract = {Accurate multiagent social simulation requires a computational model of how people incorporate their observations of real-world events into their beliefs about the state of their world. Current methods for creating such agent-based models typically rely on manual input that can be both burdensome and subjective. In this investigation, we instead pursue automated methods that can translate available data into the desired computational models. For this purpose, we use a corpus of real-world events in combination with longitudinal public opinion polls on a variety of opinion issues. We perform two experiments using automated methods taken from the literature. In our first experiment, we train maximum entropy classifiers to model changes in opinion scores as a function of real-world events. We measure and analyze the accuracy of our learned classifiers by comparing the opinion scores they generate against the opinion scores occurring in a held-out subset of our corpus. In our second experiment, we learn Bayesian networks to capture the same function.We then compare the dependency structures induced by the two methods to identify the event features that have the most significant effect on changes in public opinion.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Roemmele, Melissa
Writing Stories with Help from Recurrent Neural Networks Proceedings Article
In: AAAI Conference on Artificial Intelligence; Thirtieth AAAI Conference on Artificial Intelligence, pp. 4311 – 4312, AAAI Press, Phoenix, AZ, 2016.
@inproceedings{roemmele_writing_2016,
title = {Writing Stories with Help from Recurrent Neural Networks},
author = {Melissa Roemmele},
url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/11966},
year = {2016},
date = {2016-02-01},
booktitle = {AAAI Conference on Artificial Intelligence; Thirtieth AAAI Conference on Artificial Intelligence},
pages = {4311 – 4312},
publisher = {AAAI Press},
address = {Phoenix, AZ},
abstract = {This thesis explores the use of a recurrent neural network model for a novel story generation task. In this task, the model analyzes an ongoing story and generates a sentence that continues the story.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gordon, Andrew S.
Commonsense Interpretation of Triangle Behavior Proceedings Article
In: Thirtieth AAAI Conference on Artificial Intelligence, AAAI Press, Phoenix, AZ, 2016.
@inproceedings{gordon_commonsense_2016,
title = {Commonsense Interpretation of Triangle Behavior},
author = {Andrew S. Gordon},
url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI16/rt/metadata/11790/12152},
year = {2016},
date = {2016-02-01},
booktitle = {Thirtieth AAAI Conference on Artificial Intelligence},
publisher = {AAAI Press},
address = {Phoenix, AZ},
abstract = {The ability to infer intentions, emotions, and other unobservable psychological states from people’s behavior is a hallmark of human social cognition, and an essential capability for future Artificial Intelligence systems. The commonsense theories of psychology and sociology necessary for such inferences have been a focus of logic-based knowledge representation research, but have been difficult to employ in robust automated reasoning architectures. In this paper we model behavior interpretation as a process of logical abduction, where the reasoning task is to identify the most probable set of assumptions that logically entail the observable behavior of others, given commonsense theories of psychology and sociology. We evaluate our approach using Triangle-COPA, a benchmark suite of 100 challenge problems based on an early social psychology experiment by Fritz Heider and Marianne Simmel. Commonsense knowledge of actions, social relationships, intentions, and emotions are encoded as defeasible axioms in first-order logic. We identify sets of assumptions that logically entail observed behaviors by backchaining with these axioms to a given depth, and order these sets by their joint probability assuming conditional independence. Our approach solves almost all (91) of the 100 questions in Triangle-COPA, and demonstrates a promising approach to robust behavior interpretation that integrates both logical and probabilistic reasoning.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Scherer, Stefan
Multimodal Behavior Analytics for Interactive Technologies Journal Article
In: KI - Künstliche Intelligenz, vol. 30, no. 1, pp. 91–92, 2016, ISSN: 0933-1875, 1610-1987.
@article{scherer_multimodal_2016,
title = {Multimodal Behavior Analytics for Interactive Technologies},
author = {Stefan Scherer},
url = {http://download.springer.com/static/pdf/790/art%253A10.1007%252Fs13218-015-0401-0.pdf?originUrl=http%3A%2F%2Flink.springer.com%2Farticle%2F10.1007%2Fs13218-015-0401-0&token2=exp=1474903610 acl=%2Fstatic%2Fpdf%2F790%2Fart%25253A10.1007%25252Fs13218-015-0401-0.pdf%3ForiginUrl%3Dhttp%253A%252F%252Flink.springer.com%252Farticle%252F10.1007%252Fs13218-015-0401-0* hmac=8e31601212e82ac3ea1341f6bbddc376f14d6833e9b1df0adff03a332bb17122},
doi = {10.1007/s13218-015-0401-0},
issn = {0933-1875, 1610-1987},
year = {2016},
date = {2016-02-01},
journal = {KI - Künstliche Intelligenz},
volume = {30},
number = {1},
pages = {91–92},
abstract = {Human communication is multifaceted and information between humans is communicated on many channels in parallel. In order for a machine to become an efficient and accepted social companion, it is important that the machine understands interactive cues that not only represent direct communicative information such as spoken words but also nonverbal behavior. Hence, technologies to understand and put nonverbal communication into the context of the present interaction are essential for the advancement of human-machine interfaces [3, 4]. Multimodal behavior analytics—a transdisciplinary field of research—aims to close this gap and enables machines to automatically identify, characterize, model, and synthesize individuals’ multimodal nonverbal behavior within both human-machine as well as machine-mediated humanhuman interaction. The emerging technology of this field is relevant for a wide range of interaction applications, including but not limited to the areas of healthcare and education. Exemplarily, the characterization and association of nonverbal behavior with underlying clinical conditions, such as depression or post-traumatic stress, holds transformative potential and could change treatment and the healthcare systems efficiency significantly [6]. Within the educational context the assessment of proficiency and expertise of individuals’ social skills, in particular for those with learning disabilities or social anxiety, can help create individualized education scenarios [2, 8]. The potential of machine-assisted training for individuals with autism spectrum disorders (ASD) for example could have far reaching impacts on our society. In the following, I highlight two behavior analytics approaches that were investigated in my PhD dissertation [3] and summarized in a multimodal framework for human behavior analysis [4].},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Graesser, Arthur C; Hu, Xiangen; Nye, Benjamin D.; Sottilare, Robert A.
Intelligent Tutoring Systems, Serious Games, and the Generalized Intelligent Framework for Tutoring (GIFT) Book Section
In: Using Games and Simulations for Teaching and Assessment, pp. 58–79, Routledge, New York, NY, 2016, ISBN: 978-0-415-73787-6.
@incollection{graesser_intelligent_2016,
title = {Intelligent Tutoring Systems, Serious Games, and the Generalized Intelligent Framework for Tutoring (GIFT)},
author = {Arthur C Graesser and Xiangen Hu and Benjamin D. Nye and Robert A. Sottilare},
url = {https://www.researchgate.net/publication/304013322_Intelligent_Tutoring_Systems_Serious_Games_and_the_Generalized_Intelligent_Framework_for_Tutoring_GIFT},
isbn = {978-0-415-73787-6},
year = {2016},
date = {2016-01-01},
booktitle = {Using Games and Simulations for Teaching and Assessment},
pages = {58–79},
publisher = {Routledge},
address = {New York, NY},
abstract = {This chapter explores the prospects of integrating games with intelligent tutoring systems (ITSs). The hope is that there can be learning environments that optimize both motivation through games and deep learning through ITS technologies. Deep learning refers to the acquisition of knowledge, skills, strategies, and reasoning processes at the higher levels of Bloom’s (1956) taxonomy or the Knowledge-Learning-Instruction (KLI) framework (Koedinger, Corbett, & Perfetti, 2012), such as the application of knowledge to new cases, knowledge analysis and synthesis, problem solving, critical thinking, and other difficult cognitive processes. In contrast, shallow learning involves perceptual learning, memorization of explicit material, and mastery of simple rigid procedures. Shallow knowledge may be adequate for near transfer tests of knowledge/skills but not far transfer tests to new situations that have some modicum of complexity.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Rizzo, Albert; Talbot, Thomas
Virtual Reality Standardized Patients for Clinical Training Book Section
In: The Digital Patient, pp. 255–272, John Wiley & Sons, Inc, Hoboken, NJ, 2016, ISBN: 978-1-118-95278-8 978-1-118-95275-7.
@incollection{rizzo_virtual_2016,
title = {Virtual Reality Standardized Patients for Clinical Training},
author = {Albert Rizzo and Thomas Talbot},
url = {http://doi.wiley.com/10.1002/9781118952788.ch18},
isbn = {978-1-118-95278-8 978-1-118-95275-7},
year = {2016},
date = {2016-01-01},
booktitle = {The Digital Patient},
pages = {255–272},
publisher = {John Wiley & Sons, Inc},
address = {Hoboken, NJ},
abstract = {There are several quite distinct educational approaches that are all called a virtual patient. It includes case presentations, interactive patient scenarios, virtual patient games, human standardized patients (HSPs), high-fidelity software simulations, high-fidelity manikins, and virtual human (VH) conversational agents. VH conversations are possible that include an avatar that responds to pre-selected choices; such an interview is called a structured encounter. Most VSPs attempted to date have been on traditional computers. With the increased prevalence of mobile devices, it is logical to consider the migration of VSP technology to phones and tablets. Future distant recognition (DSR) systems will require a high level of individual speaker discrimination and will likely adopt microphone array-based acoustic beam forming technology. Future success may no longer be rate-limited by the pace of technology, but by the creativity and innovation of educators who will create compelling VSP experiences and curricula.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Kaplan, Jonas T.; Gimbel, Sarah I.; Dehghani, Morteza; Immordino-Yang, Mary Helen; Sagae, Kenji; Wong, Jennifer D.; Tipper, Christine M.; Damasio, Hanna; Gordon, Andrew S.; Damasio, Antonio
Processing Narratives Concerning Protected Values: A Cross-Cultural Investigation of Neural Correlates Journal Article
In: Cerebral Cortex, 2016, ISSN: 1047-3211, 1460-2199.
@article{kaplan_processing_2016,
title = {Processing Narratives Concerning Protected Values: A Cross-Cultural Investigation of Neural Correlates},
author = {Jonas T. Kaplan and Sarah I. Gimbel and Morteza Dehghani and Mary Helen Immordino-Yang and Kenji Sagae and Jennifer D. Wong and Christine M. Tipper and Hanna Damasio and Andrew S. Gordon and Antonio Damasio},
url = {http://www.cercor.oxfordjournals.org/lookup/doi/10.1093/cercor/bhv325},
doi = {10.1093/cercor/bhv325},
issn = {1047-3211, 1460-2199},
year = {2016},
date = {2016-01-01},
journal = {Cerebral Cortex},
abstract = {Narratives are an important component of culture and play a central role in transmitting social values. Little is known, however, about how the brain of a listener/reader processes narratives. A receiver's response to narration is influenced by the narrator's framing and appeal to values. Narratives that appeal to “protected values,” including core personal, national, or religious values, may be particularly effective at influencing receivers. Protected values resist compromise and are tied with identity, affective value, moral decision-making, and other aspects of social cognition. Here, we investigated the neural mechanisms underlying reactions to protected values in narratives. During fMRI scanning, we presented 78 American, Chinese, and Iranian participants with real-life stories distilled from a corpus of over 20 million weblogs. Reading these stories engaged the posterior medial, medial prefrontal, and temporo-parietal cortices. When participants believed that the protagonist was appealing to a protected value, signal in these regions was increased compared with when no protected value was perceived, possibly reflecting the intensive and iterative search required to process this material. The effect strength also varied across groups, potentially reflecting cultural differences in the degree of concern for protected values.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cukor, Judith; Gerardi, Maryrose; Alley, Stephanie; Reist, Christopher; Roy, Michael; Rothbaum, Barbara O.; Difede, JoAnn; Rizzo, Albert
Virtual Reality Exposure Therapy for Combat-Related PTSD Book Section
In: Posttraumatic Stress Disorder and Related Diseases in Combat Veterans, pp. 69–83, Springer International Publishing, Cham, Switzerland, 2016, ISBN: 978-3-319-22984-3 978-3-319-22985-0.
@incollection{cukor_virtual_2016,
title = {Virtual Reality Exposure Therapy for Combat-Related PTSD},
author = {Judith Cukor and Maryrose Gerardi and Stephanie Alley and Christopher Reist and Michael Roy and Barbara O. Rothbaum and JoAnn Difede and Albert Rizzo},
url = {http://link.springer.com/10.1007/978-3-319-22985-0_7},
isbn = {978-3-319-22984-3 978-3-319-22985-0},
year = {2016},
date = {2016-01-01},
booktitle = {Posttraumatic Stress Disorder and Related Diseases in Combat Veterans},
pages = {69–83},
publisher = {Springer International Publishing},
address = {Cham, Switzerland},
abstract = {War is perhaps one of the most challenging situations that a human being can experience. The physical, emotional, cognitive, and psychological demands of a combat environment place enormous stress on even the best-prepared military personnel. Numerous reports indicate that the incidence of posttraumatic stress disorder (PTSD) in returning Operation Enduring Freedom/Operation Iraqi Freedom (OEF/OIF) military personnel is significant. This has served to motivate research on how to better develop and disseminate evidence-based treatments for PTSD that leverage the unique features available with virtual reality (VR) technology. VR-delivered exposure therapy for PTSD is currently being used to treat combatand terrorist attack-related PTSD with initial reports of positive outcomes. This chapter presents a brief overview and rationale for the use of VR exposure for combat-related PTSD and describes the Virtual Iraq/Afghanistan exposure therapy system. This includes a short review of the previous literature, a description of the system components and the treatment protocol, and a case presentation. VR offers an alternative format for delivering exposure-based therapies for PTSD that may appeal to certain service members and veterans who grew up “digital” and who might be inclined to seek treatment in this fashion.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Venek, Verena; Scherer, Stefan; Morency, Louis-Philippe; Rizzo, Albert; Pestian, John
Adolescent Suicidal Risk Assessment in Clinician-Patient Interaction Journal Article
In: IEEE Transactions on Affective Computing, vol. PP, no. 99, 2016, ISSN: 1949-3045.
@article{venek_adolescent_2016,
title = {Adolescent Suicidal Risk Assessment in Clinician-Patient Interaction},
author = {Verena Venek and Stefan Scherer and Louis-Philippe Morency and Albert Rizzo and John Pestian},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7384418},
doi = {10.1109/TAFFC.2016.2518665},
issn = {1949-3045},
year = {2016},
date = {2016-01-01},
journal = {IEEE Transactions on Affective Computing},
volume = {PP},
number = {99},
abstract = {Youth suicide is a major public health problem. It is the third leading cause of death in the United States for ages 13 through 18. Many adolescents that face suicidal thoughts or make a suicide plan never seek professional care or help. Within this work, we evaluate both verbal and nonverbal responses to a five-item ubiquitous questionnaire to identify and assess suicidal risk of adolescents. We utilize a machine learning approach to identify suicidal from non-suicidal speech as well as characterize adolescents that repeatedly attempted suicide in the past. Our findings investigate both verbal and nonverbal behavior information of the face-to-face clinician-patient interaction. We investigate 60 audio-recorded dyadic clinician-patient interviews of 30 suicidal (13 repeaters and 17 non-repeaters) and 30 non-suicidal adolescents. The interaction between clinician and adolescents is statistically analyzed to reveal differences between suicidal vs. non-suicidal adolescents and to investigate suicidal repeaters’ behaviors in comparison to suicidal non-repeaters. By using a hierarchical classifier we were able to show that the verbal responses to the ubiquitous questions sections of the interviews were useful to discriminate suicidal and non-suicidal patients. However, to additionally classify suicidal repeaters and suicidal non-repeaters more information especially nonverbal information is required.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Scherer, Stefan; Lucas, Gale M.; Gratch, Jonathan; Rizzo, Albert Skip; Morency, Louis-Philippe
Self-reported symptoms of depression and PTSD are associated with reduced vowel space in screening interviews Journal Article
In: IEEE Transactions on Affective Computing, vol. 7, no. 1, pp. 59–73, 2016, ISSN: 1949-3045.
@article{scherer_self-reported_2016,
title = {Self-reported symptoms of depression and PTSD are associated with reduced vowel space in screening interviews},
author = {Stefan Scherer and Gale M. Lucas and Jonathan Gratch and Albert Skip Rizzo and Louis-Philippe Morency},
url = {http://ieeexplore.ieee.org/document/7117386/?arnumber=7117386},
doi = {10.1109/TAFFC.2015.2440264},
issn = {1949-3045},
year = {2016},
date = {2016-01-01},
journal = {IEEE Transactions on Affective Computing},
volume = {7},
number = {1},
pages = {59–73},
abstract = {Reduced frequency range in vowel production is a well documented speech characteristic of individuals’ with psychological and neurological disorders. Affective disorders such as depression and post-traumatic stress disorder (PTSD) are known to influence motor control and in particular speech production. The assessment and documentation of reduced vowel space and reduced expressivity often either rely on subjective assessments or on analysis of speech under constrained laboratory conditions (e.g.sustained vowel production, reading tasks). These constraints render the analysis of such measures expensive and impractical. Within this work, we investigate an automatic unsupervised machine learning based approach to assess a speaker’s vowel space. Our experiments are based on recordings of 253 individuals. Symptoms of depression and PTSD are assessed using standard self-assessment questionnaires and their cut-off scores. The experiments show a significantly reduced vowel space in subjects that scored positively on the questionnaires. We show the measure’s statistical robustness against varying demographics of individuals and articulation rate. The reduced vowel space for subjects with symptoms of depression can be explained by the common condition of psychomotor retardation influencing articulation and motor control. These findings could potentially support treatment of affective disorders, like depression and PTSD in the future.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Filter
2001
Gordon, Andrew S.
Browsing Image Collections with Representations of Commonsense Activities Journal Article
In: Journal of the American Society for Information Science and Technology, vol. 52, no. 11, pp. 925–929, 2001.
Abstract | Links | BibTeX | Tags: The Narrative Group
@article{gordon_browsing_2001,
title = {Browsing Image Collections with Representations of Commonsense Activities},
author = {Andrew S. Gordon},
url = {http://ict.usc.edu/pubs/Browsing%20Image%20Collections%20with%20Representations%20of%20Commonsense%20Activities.PDF},
year = {2001},
date = {2001-01-01},
journal = {Journal of the American Society for Information Science and Technology},
volume = {52},
number = {11},
pages = {925–929},
abstract = {To support browsing-based subject access to image collections, it is necessary to provide users with networks of subject terms that are organized in an intuitive, richly interconnected manner. A principled approach to this task is to organize the subject terms by their relationship to activity contexts that are commonly understood among users. This article describes a methodology for creating networks of subject terms by manually representing a large number of common-sense activities that are broadly related to image subject terms. The application of this methodology to the Library of Congress Thesaurus for Graphic Materials produced 768 representations that supported users of a prototype browsing-based retrieval system in searching large, indexed photograph collections.},
keywords = {The Narrative Group},
pubstate = {published},
tppubtype = {article}
}
Gratch, Jonathan; Marsella, Stacy C.
Tears and Fears: Modeling emotions and emotional behaviors in synthetic agents Proceedings Article
In: Proceedings of the 5th International Conference on Autonomous Agents, pp. 278–285, Montreal, Canada, 2001.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{gratch_tears_2001,
title = {Tears and Fears: Modeling emotions and emotional behaviors in synthetic agents},
author = {Jonathan Gratch and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/Tears%20and%20Fears-%20Modeling%20emotions%20and%20emotional%20behaviors%20in%20synthetic%20agents.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Proceedings of the 5th International Conference on Autonomous Agents},
pages = {278–285},
address = {Montreal, Canada},
abstract = {Emotions play a critical role in creating engaging and believable characters to populate virtual worlds. Our goal is to create general computational models to support characters that act in virtual environments, make decisions, but whose behavior also suggests an underlying emotional current. In service of this goal, we integrate two complementary approaches to emotional modeling into a single unified system. Gratch's Émile system focuses on the problem of emotional appraisal: how emotions arise from an evaluation of how environmental events relate to an agent's plans and goals. Marsella et al. 's IPD system focuses more on the impact of emotions on behavior, including the impact on the physical expressions of emotional state through suitable choice of gestures and body language. This integrated model is layered atop Steve, a pedagogical agent architecture, and exercised within the context of the Mission Rehearsal Exercise, a prototype system designed to teach decision- making skills in highly evocative situations.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Hawkins, Tim; Cohen, Jonathan; Debevec, Paul
A Photometric Approach to Digitizing Cultural Artifacts Proceedings Article
In: Proceedings of 2nd International Symposium on Virtual Reality, Archaeology and Cultural Heritage, Glyfada, Greece, 2001.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{hawkins_photometric_2001,
title = {A Photometric Approach to Digitizing Cultural Artifacts},
author = {Tim Hawkins and Jonathan Cohen and Paul Debevec},
url = {http://ict.usc.edu/pubs/A%20Photometric%20Approach%20to%20Digitizing%20Cultural%20Artifacts.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Proceedings of 2nd International Symposium on Virtual Reality, Archaeology and Cultural Heritage},
address = {Glyfada, Greece},
abstract = {In this paper we present a photometry-based approach to the digital documentation of cultural artifacts. Rather than representing an artifact as a geometric model with spatially varying reflectance properties, we instead propose directly representing the artifact in terms of its reflectance field - the manner in which it transforms light into images. The principal device employed in our technique is a computer-controlled lighting apparatus which quickly illuminates an artifact from an exhaustive set of incident illumination directions and a set of digital video cameras which record the artifact's appearance under these forms of illumination. From this database of recorded images, we compute linear combinations of the captured images to synthetically illuminate the object under arbitrary forms of complex incident illumination, correctly capturing the effects of specular reflection, subsurface scattering, self-shadowing, mutual illumination, and complex BRDF's often present in cultural artifacts. We also describe a computer application that allows users to realistically and interactively relight digitized artifacts.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Lee, C. M.; Narayanan, Shrikanth; Pieraccin, R.
Recognition of Negative Emotions from the Speech Signal Proceedings Article
In: Proceedings of Automatic Speech Recognition and Understanding Workshop (ASRU 2001), 2001.
Abstract | Links | BibTeX | Tags:
@inproceedings{lee_recognition_2001,
title = {Recognition of Negative Emotions from the Speech Signal},
author = {C. M. Lee and Shrikanth Narayanan and R. Pieraccin},
url = {http://ict.usc.edu/pubs/Recognition%20of%20Negative%20Emotions%20from%20the%20Speech%20Signal.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Proceedings of Automatic Speech Recognition and Understanding Workshop (ASRU 2001)},
abstract = {This paper reports on methods for automatic classification of spoken utterances based on the emotional state of the speaker. The data set used for the analysis comes from a corpus of human- machine dialogs recorded from a commercial application deployed by SpeechWorks. Linear discriminant classification with Gaussian class-conditional probability distribution and knearest neighborhood methods are used to classify utterances into two basic emotion states, negative and non-negative. The features used by the classifiers are utterance-level statistics of the fundamental frequency and energy of the speech signal. To improve classification performance, two specific feature selection methods are used; namely, promising first selection and forward feature selection. Principal component analysis is used to reduce the dimensionality of the features while maximizing classification accuracy. Improvements obtained by feature selection and PCA are reported in this paper. We reported the results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hawkins, Tim; Cohen, Jonathan; Tchou, Chris; Debevec, Paul
Light Stage 2.0 Proceedings Article
In: SIGGRAPH Technical Sketches, pp. 217, 2001.
Links | BibTeX | Tags: Graphics
@inproceedings{hawkins_light_2001,
title = {Light Stage 2.0},
author = {Tim Hawkins and Jonathan Cohen and Chris Tchou and Paul Debevec},
url = {http://ict.usc.edu/pubs/Light%20Stage%202.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {SIGGRAPH Technical Sketches},
pages = {217},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Olsen, Mari; Traum, David; Ess-Dykema, Carol Van; Weinberg, Amy
Implicit Cues for Explicit Generation: Using Telicity as a Cue for Tense Structure in Chinese to English MT System Proceedings Article
In: Machine Translation Summit VIII, Santiago de Compostela, Spain, 2001.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{olsen_implicit_2001,
title = {Implicit Cues for Explicit Generation: Using Telicity as a Cue for Tense Structure in Chinese to English MT System},
author = {Mari Olsen and David Traum and Carol Van Ess-Dykema and Amy Weinberg},
url = {http://ict.usc.edu/pubs/Implicit%20Cues%20for%20Explicit%20Generation-%20Using%20Telicity%20as%20a%20Cue%20for%20Tense%20Structure%20in%20Chinese%20to%20English%20MT%20System.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Machine Translation Summit VIII},
address = {Santiago de Compostela, Spain},
abstract = {In translating from Chinese to English, tense and other temporal information must be inferred from other grammatical and lexical cues. Tense information is crucial to providing accurate and fluent translations into English. Perfective and imperfective grammatical aspect markers can provide cues to temporal structure, but such information is optional in Chinese and is not present in the majority of sentences. We report on a project that assesses the relative contribution of the lexical aspect features of (a)telicity reflected in the Lexical Conceptual Structure of the input text, versus more overt aspectual and adverbial markers of tense, to suggest tense structure in the English translation of a Chinese newspaper corpus. Incorporating this information allows a 20% to 35% boost in the accuracy of tense relization with the best accuracy rate of 92% on a corpus of Chinese articles.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Yang, Dai; Ai, Hongmei; Kyriakakis, Chris; Kuo, C. -C. Jay
Embedded High-Quality Multichannel Audio Coding Proceedings Article
In: Conference on Media Processors, Symposium on Electronic Imaging, San Jose, CA, 2001.
Abstract | Links | BibTeX | Tags:
@inproceedings{yang_embedded_2001,
title = {Embedded High-Quality Multichannel Audio Coding},
author = {Dai Yang and Hongmei Ai and Chris Kyriakakis and C. -C. Jay Kuo},
url = {http://ict.usc.edu/pubs/Embedded%20High-Quality%20Multichannel%20Audio%20Coding.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Conference on Media Processors, Symposium on Electronic Imaging},
address = {San Jose, CA},
abstract = {An embedded high-quality multi-channel audio coding algorithms is proposed in this research. The Karhunen-Loeve Transform (KLT) is applied to multichannel audio signals in the pre-processing stage to remove inter-channel redundancy. Then, after processing of several audio coding blocks, transformed coefficients are layered quantized and the bit stream is ordered according to their importance. The multichannel audio bit stream generated by the propoesed algorithm has a fully progressive property, which is highly desirable for audio multicast applications in heterogenous networks. Experimental results show that, compared with the MPEG Advanced Audio Coding (AAC) algorithm, the proposed algorithm achieves a better performance with both the objective MNR (Mask-to-Noise-Ratio) measurement and the subjective listening test at several different bit rates.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Waese, Jamie; Debevec, Paul
A Real Time High Dynamic Range Light Probe Proceedings Article
In: SIGGRAPH Technical Sketches, 2001.
Links | BibTeX | Tags: Graphics
@inproceedings{waese_real_2001,
title = {A Real Time High Dynamic Range Light Probe},
author = {Jamie Waese and Paul Debevec},
url = {http://ict.usc.edu/pubs/A%20Real%20Time%20High%20Dynamic%20Range%20Light%20Probe.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {SIGGRAPH Technical Sketches},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Bharitkar, Sunil; Kyriakakis, Chris
A Cluster Centroid Method for Room Response Equalization at Multiple Locations Proceedings Article
In: IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics, pp. 55–58, New Platz, NY, 2001, ISBN: 0-7803-7126-7.
Abstract | Links | BibTeX | Tags:
@inproceedings{bharitkar_cluster_2001,
title = {A Cluster Centroid Method for Room Response Equalization at Multiple Locations},
author = {Sunil Bharitkar and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/A%20CLUSTER%20CENTROID%20METHOD%20FOR%20ROOM%20RESPONSE%20EQUALIZATION%20AT%20MULTIPLE%20LOCATIONS.pdf},
isbn = {0-7803-7126-7},
year = {2001},
date = {2001-01-01},
booktitle = {IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics},
pages = {55–58},
address = {New Platz, NY},
abstract = {In this paper we address the problem of simultaneous room response equalization for multiple listeners. Traditional approaches to this problem have used a single microphone at the listening position to measure impulse responses from a loudspeaker and then use an inverse filter to correct the frequency response. The problem with that approach is that it only works well for that one point and in most cases is not practical even for one listener with a typical ear spacing of 18 cm. It does not work at all for other listeners in the room, or if the listener changes positions even slightly. We propose a new approach that is based on the Fuzzy c-means clustering technique. We use this method to design equalization filters and demonstrate that we can achieve better equalization performance for several locations in the room simultaneously as compared to single point or simple averaging methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Srinivasamurthy, Naveen; Narayanan, Shrikanth; Ortega, Antonio
Use of Model Transformations for Distributed Speech Recognition Proceedings Article
In: 4th ISCA Tutorial and Research Workshop on Speech Synthesis, pp. 113–116, Sophia Antipolis, France, 2001.
Abstract | Links | BibTeX | Tags:
@inproceedings{srinivasamurthy_use_2001,
title = {Use of Model Transformations for Distributed Speech Recognition},
author = {Naveen Srinivasamurthy and Shrikanth Narayanan and Antonio Ortega},
url = {http://ict.usc.edu/pubs/Use%20of%20Model%20Transformations%20for%20Distributed%20Speech%20Recognition.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {4th ISCA Tutorial and Research Workshop on Speech Synthesis},
pages = {113–116},
address = {Sophia Antipolis, France},
abstract = {Due to bandwidth limitations, the speech recognizer in distributed speech recognition (DSR) applications has to use encoded speech - either traditional speech encoding or speech encoding optimized for recognition. The penalty incurred in reducing the bitrate is degradation in speech recognition performance. The diversity of the applications using DSR implies that a variety of speech encoders can be used to compress speech. By treating the encoder variability as a mismatch we propose using model transformation to reduce the speech recognition performance degradation. The advantage of using model transformation is that only a single model set needs to be trained at the server, which can be adapted on the fly to the input speech data. We were able to reduce the word error rate by 61.9%, 63.3% and 56.3% for MELP, GSM and MFCC-encoded data, respectively, by using MAP adaptation, which shows the generality of our proposed scheme.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Damiano, Rossana; Traum, David
Anticipatory planning for decision-theoretic grounding and task advancement in mixed-initiative dialogue systems Proceedings Article
In: NAACL 2001 Workshop on Adaptation in Dialogue Systems, 2001.
Links | BibTeX | Tags: Virtual Humans
@inproceedings{damiano_anticipatory_2001,
title = {Anticipatory planning for decision-theoretic grounding and task advancement in mixed-initiative dialogue systems},
author = {Rossana Damiano and David Traum},
url = {http://ict.usc.edu/pubs/Anticipatory%20planning%20for%20decision-theoretic%20grounding%20and%20task%20advancement%20in%20mixed-initiative%20dialogue%20systems.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {NAACL 2001 Workshop on Adaptation in Dialogue Systems},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Marsella, Stacy C.; Gratch, Jonathan
Modeling the Interplay of Emotions and Plans in Multi-Agent Simulations Proceedings Article
In: Proceedings of 23rd Annual Conference of the Cognitive Science Society, Edinburgh, Scotland, 2001.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{marsella_modeling_2001,
title = {Modeling the Interplay of Emotions and Plans in Multi-Agent Simulations},
author = {Stacy C. Marsella and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Modeling%20the%20Interplay%20of%20Emotions%20and%20Plans%20in%20Multi-Agent%20Simulations.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {Proceedings of 23rd Annual Conference of the Cognitive Science Society},
address = {Edinburgh, Scotland},
abstract = {The goal of this research is to create general computational models of the interplay between affect, cognition and behavior. These models are being designed to support characters that act in virtual environments, make decisions, but whose behavior also suggests an underlying emotional current. We attempt to capture both the cognitive and behavioral aspects of emotion, circumscribed to the role emotions play in the performance of concrete physical tasks. We address how emotions arise from an evaluation of the relationship between environmental events and an agent's plans and goals, as well as the impact of emotions on behavior, in particular the impact on the physical expressions of emotional state through suitable choice of gestures and body language. The approach is illustrated within a virtual reality training environment.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Yang, Dai; Ai, Hongmei; Kyriakakis, Chris; Kuo, C. -C. Jay
Adaptive Karhunen-Loeve Transform for Enhanced Multichannel Audio Coding Proceedings Article
In: SPIE, San Diego, CA, 2001.
Abstract | Links | BibTeX | Tags:
@inproceedings{yang_adaptive_2001,
title = {Adaptive Karhunen-Loeve Transform for Enhanced Multichannel Audio Coding},
author = {Dai Yang and Hongmei Ai and Chris Kyriakakis and C. -C. Jay Kuo},
url = {http://ict.usc.edu/pubs/Adaptive%20Karhunen-Loeve%20Transform%20for%20Enhanced%20Multichannel%20Audio%20Coding.pdf},
year = {2001},
date = {2001-01-01},
booktitle = {SPIE},
address = {San Diego, CA},
abstract = {A modified MPEG Advanced Audio Coding (AAC) scheme based on the Karhunen-Loeve transform (KLT) to remove inter-channel redundancy, which is called the MAACKL method, has been proposed in our previous work. However, a straightforward coding of elements of the KLT matrix generates about 240 bits per matrix for typical 5 channel audio contents. Such an overhead is too expensive so that it prevents MAACKL from updating KLT dynamically in a short period of time. In this research, we study the de-correlation efficiency of adaptive KLT as well as an efficient way to encode elements of the KLT matrix via vector quantization. The effect due to different quantization accuracy and adaptation period is examined carefully. It is demonstrated that with the smallest possible number of bits per matrix and a moderately long KLT adaptation time, the MAACKL algorithm can still generate a very good coding performance.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sadek, Ramy; Miraglia, Dave; Morie, Jacquelyn
3D Sound Design and Technology for the Sensory Environments Evaluations Project: Phase 1 Technical Report
University of Southern California Institute for Creative Technologies Marina del Rey, CA, no. ICT TR 01.2001, 2001.
@techreport{sadek_3d_2001,
title = {3D Sound Design and Technology for the Sensory Environments Evaluations Project: Phase 1},
author = {Ramy Sadek and Dave Miraglia and Jacquelyn Morie},
url = {http://ict.usc.edu/pubs/ICT-TR-01-2001.pdf},
year = {2001},
date = {2001-01-01},
number = {ICT TR 01.2001},
address = {Marina del Rey, CA},
institution = {University of Southern California Institute for Creative Technologies},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2000
Debevec, Paul; Hawkins, Tim; Tchou, Chris; Duiker, Haarm-Pieter; Sarokin, Westley
Acquiring the Reflectance Field of a Human Face Proceedings Article
In: SIGGRAPH, New Orleans, LA, 2000.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{debevec_acquiring_2000,
title = {Acquiring the Reflectance Field of a Human Face},
author = {Paul Debevec and Tim Hawkins and Chris Tchou and Haarm-Pieter Duiker and Westley Sarokin},
url = {http://ict.usc.edu/pubs/Acquiring%20the%20Re%EF%AC%82ectance%20Field%20of%20a%20Human%20Face.pdf},
year = {2000},
date = {2000-07-01},
booktitle = {SIGGRAPH},
address = {New Orleans, LA},
abstract = {We present a method to acquire the reflectance field of a human face and use these measurements to render the face under arbitrary changes in lighting and viewpoint. We first acquire images of the face from a small set of viewpoints under a dense sampling of incident illumination directions using a light stage. We then construct a reflectance function image for each observed image pixel from its values over the space of illumination directions. From the reflectance functions, we can directly generate images of the face from the original viewpoints in any form of sampled or computed illumination. To change the viewpoint, we use a model of skin reflectance to estimate the appearance of the reflectance functions for novel viewpoints. We demonstrate the technique with synthetic renderings of a person's face under novel illumination and viewpoints.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Bharitkar, Sunil; Kyriakakis, Chris
Selective Signal Cancellation for Multiple Listener Audio Applications: An Information Theory Approach Proceedings Article
In: IEEE International Conference Multimedia and Expo, New York, NY, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{bharitkar_selective_2000,
title = {Selective Signal Cancellation for Multiple Listener Audio Applications: An Information Theory Approach},
author = {Sunil Bharitkar and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/SELECTIVE%20SIGNAL%20CANCELLATION%20FOR%20MULTIPLE-LISTENER%20AUDIO%20APPLICATIONS-%20AN%20INFORMATION%20THEORY%20APPROACH.pdf},
year = {2000},
date = {2000-07-01},
booktitle = {IEEE International Conference Multimedia and Expo},
address = {New York, NY},
abstract = {Selectively canceling signals at specific locations within an acoustical environment with multiple listeners is of significant importance for home theater, teleconferencing, office, industrial and other applications. The traditional noise cancellation approach is impractical for such applications because it requires sensors that must be placed on the listeners. In this paper we propose an alternative method to minimize signal power in a given location and maximize signal power in another location of interest. A key advantage of this approach would be the need to eliminate sensors. We investigate the use of an information theoretic criterion known as mutual information to design filter coefficients that selectively cancel a signal in one audio channel, and transmit it in another (complementary) channel. Our results show an improvement in power gain at one location in the room relative to the other.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Human-like behavior, alas, demands human-like intellect Proceedings Article
In: Agents 2000 Workshop on Achieving Human-like Behavior in Interactive Animated Agents, Barcelona, Spain, 2000.
Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_human-like_2000,
title = {Human-like behavior, alas, demands human-like intellect},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Human-like%20behavior%20alas%20demands%20human-like%20intellect.pdf},
year = {2000},
date = {2000-06-01},
booktitle = {Agents 2000 Workshop on Achieving Human-like Behavior in Interactive Animated Agents},
address = {Barcelona, Spain},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Moutchtaris, Athanasios; Reveliotis, Panagiotis; Kyriakakis, Chris
Inverse Filter Design for Immersive Audio Rendering Over Loudspeakers Journal Article
In: IEEE Transactions on Multimedia, vol. 2, no. 2, pp. 77–87, 2000.
Abstract | Links | BibTeX | Tags:
@article{moutchtaris_inverse_2000,
title = {Inverse Filter Design for Immersive Audio Rendering Over Loudspeakers},
author = {Athanasios Moutchtaris and Panagiotis Reveliotis and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/Inverse%20Filter%20Design%20for%20Immersive%20Audio%20Rendering%20Over%20Loudspeakers.pdf},
year = {2000},
date = {2000-06-01},
journal = {IEEE Transactions on Multimedia},
volume = {2},
number = {2},
pages = {77–87},
abstract = {Immersive audio systems can be used to render virtual sound sources in three-dimensional (3-D) space around a listener. This is achieved by simulating the head-related transfer function (HRTF) amplitude and phase characteristics using digital filters. In this paper, we examine certain key signal processing considerations in spatial sound rendering over headphones and loudspeakers. We address the problem of crosstalk inherent in loudspeaker rendering and examine two methods for implementing crosstalk cancellation and loudspeaker frequency response inversion in real time. We demonstrate that it is possible to achieve crosstalk cancellation of 30 dB using both methods, but one of the two (the Fast RLS Transversal Filter Method) offers a significant advantage in terms of computational efficiency. Our analysis is easily extendable to nonsymmetric listening positions and moving listeners.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hill, Randall W.; Gratch, Jonathan; Rosenbloom, Paul
Flexible Group Behavior: Virtual Commanders for Synthetic Battlespaces Proceedings Article
In: Proceedings of the 4th International Conference on Autonomous Agents, Barcelona, Spain, 2000.
Abstract | Links | BibTeX | Tags: CogArch, Cognitive Architecture, Social Simulation, Virtual Humans
@inproceedings{hill_flexible_2000,
title = {Flexible Group Behavior: Virtual Commanders for Synthetic Battlespaces},
author = {Randall W. Hill and Jonathan Gratch and Paul Rosenbloom},
url = {http://ict.usc.edu/pubs/Flexible%20Group%20Behavior-%20Virtual%20Commanders%20for%20Synthetic%20Battlespaces.pdf},
year = {2000},
date = {2000-06-01},
booktitle = {Proceedings of the 4th International Conference on Autonomous Agents},
address = {Barcelona, Spain},
abstract = {This paper describes a project to develop autonomous commander agents for synthetic battlespaces. The commander agents plan missions, monitor their execution, and replan when necessary. To reason about the social aspects of group behavior, the commanders take various social stances that enable them to collaborate with friends, exercise or defer to authority, and thwart their foes. The purpose of this paper is to describe these capabilities and how they came to be through a series of lessons learned while developing autonomous agents for this domain.},
keywords = {CogArch, Cognitive Architecture, Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Kim, Youngjun; Hill, Randall W.; Gratch, Jonathan
How Long Can an Agent Look Away From a Target? Proceedings Article
In: 9th Conference on Computer Generated Forces and Behavioral Representation, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{kim_how_2000,
title = {How Long Can an Agent Look Away From a Target?},
author = {Youngjun Kim and Randall W. Hill and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/how%20long%20can%20you%20look%20away%20from%20a%20target.pdf},
year = {2000},
date = {2000-05-01},
booktitle = {9th Conference on Computer Generated Forces and Behavioral Representation},
abstract = {Situation awareness (SA) is the perception of the elements in the environment within a volume of time and space, the comprehension of their meaning, and the projection of their status in the near future [3]. Although the impact of situation awareness and assessment on humans in complex systems is clear, no one theory for SA has been developed. A critical aspect of the SA problem is that agents must construct an overall view of a dynamically changing world using limited sensor channels. For instance, a (virtual) pilot, who visually tracks the location and direction of several vehicles that he cannot see simultaneously, must shift its visual field of view to scan the environment and to sense the situation involved. How he directs his attention, for how long, and how he efficiently reacquires targets is the central question we address in this paper. We describe the perceptual coordination that helps a virtual pilot efficiently track one or more objects. In SA, it is important for a virtual pilot having a limited visual field of view to gather more information from its environment and to choose appropriate actions to take in the environment without losing the target.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Georgiou, Panayiotis G.; Kyriakakis, Chris
A Multiple Input Single Output Model for Rendering Virtual Sound Sources in Real Time Proceedings Article
In: Proceedings of ICME 2000, New York, NY, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{georgiou_multiple_2000,
title = {A Multiple Input Single Output Model for Rendering Virtual Sound Sources in Real Time},
author = {Panayiotis G. Georgiou and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/A%20MULTIPLE%20INPUT%20SINGLE%20OUTPUT%20MODEL%20FOR%20RENDERING%20VIRTUAL%20SOUND%20SOURCES%20IN%20REAL%20TIME.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of ICME 2000},
address = {New York, NY},
abstract = {Accurate localization of sound in 3-D space is based on variations in the spectrum of sound sources. These variations arise mainly from reflection and diffraction effects caused by the pinnae and are described through a set of Head-Related Transfer Functions (HRTF’s) that are unique for each azimuth and elevation angle. A virtual sound source can be rendered in the desired location by filtering with the corresponding HRTF for each ear. Previous work on HRTF modeling has mainly focused on the methods that attempt to model each transfer function individually. These methods are generally computationally-complex and cannot be used for real-time spatial rendering of multiple moving sources. In this work we provide an alternative approach, which uses a multiple input single output state space system to creat a combined model of the HRTF’s for all directions. This method exploits the similarities among the different HRTF’s to achieve a significant reduction in the model size with a minimum loss of accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Èmile: Marshalling Passions in Training and Education Proceedings Article
In: Proceedings of the 4th International Conference on Autonomous Agents, pp. 325–332, Barcelona, Spain, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_emile_2000,
title = {Èmile: Marshalling Passions in Training and Education},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Emile-%20Marshalling%20Passions%20in%20Training%20and%20Education.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the 4th International Conference on Autonomous Agents},
pages = {325–332},
address = {Barcelona, Spain},
abstract = {Emotional reasoning can be an important contribution to automated tutoring and training systems. This paper describes �mile, a model of emotional reasoning that builds upon existing approaches and significantly generalizes and extends their capabilities. The main contribution is to show how an explicit planning model allows a more general treatment of several stages of the reasoning process. The model supports educational applications by allowing agents to appraise the emotional significance of events as they relate to students' (or their own) plans and goals, model and predict the emotional state of others, and alter behavior accordingly.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Modeling the Interplay Between Emotion and Decision-Making Proceedings Article
In: Proceedings of the 9th Conference on Computer Generated Forces and Behavioral Representation, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_modeling_2000,
title = {Modeling the Interplay Between Emotion and Decision-Making},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Modeling%20the%20Interplay%20Between%20Emotion%20and%20Decision-Making.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the 9th Conference on Computer Generated Forces and Behavioral Representation},
abstract = {Current models of computer-generated forces are limited by their inability to model many of the moderators that influence the performance of real troops in the field such as the effects of stress, emotion, and individual differences. This article discusses an extension to our command and control modeling architecture that begins to address how behavioral moderators influence the command decision-making process. Our Soar-Cfor command architecture was developed under the STOW and ASTT programs to support distributed command and control decision-making in the domain of army aviation planning. We have recently extended this architecture to model how people appraise the emotional significance of events and how these events influence decision making.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Scholer, Andrew; Rickel, Jeff; Angros, Richard Jr.; Johnson, W. Lewis
Learning Domain Knowledge for Teaching Procedural Tasks Proceedings Article
In: AAAI-2000 Fall Symposium on Learning How to Do Things, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{scholer_learning_2000,
title = {Learning Domain Knowledge for Teaching Procedural Tasks},
author = {Andrew Scholer and Jeff Rickel and Richard Jr. Angros and W. Lewis Johnson},
url = {http://ict.usc.edu/pubs/Learning%20Domain%20Knowledge%20for%20Teaching%20Procedural%20Tasks.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {AAAI-2000 Fall Symposium on Learning How to Do Things},
abstract = {Providing domain knowledge needed by intelligent tutoring systems to teach a procedure to students is traditionally a difficult and time consuming task. This paper presents a system for making this process easier by allowing the automated tutor to acquire the knowledge it needs through a combination of programming by demonstration, autonomous experimentation, and direct instruction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Socially Situated Planning Book Section
In: Socially Intelligent Agents, Multiagent Systems, Artificial Societies, and Simulated Organizations, vol. 3, pp. 181–188, AAAI Fall Symposium on Socially Intelligent Agents - The Human in the Loop, North Falmouth, MA, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@incollection{gratch_socially_2000,
title = {Socially Situated Planning},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Socially%20Situated%20Planning.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Socially Intelligent Agents, Multiagent Systems, Artificial Societies, and Simulated Organizations},
volume = {3},
pages = {181–188},
address = {AAAI Fall Symposium on Socially Intelligent Agents - The Human in the Loop, North Falmouth, MA},
abstract = {Introduction: Virtual environments such as training simulators and video games do an impressive job at modeling the physical dynamics of synthetic worlds but fall short when modeling the social dynamics of anything but the most impoverished human encounters. Yet the social dimension is at least as important as good graphics for creating an engaging game or effective training tool. Commercial flight simulators accurately model the technical aspects of flight but many aviation disasters arise from social breakdowns: poor management skills in the cockpit, or the effects of stress and emotion. Perhaps the biggest consumer of simulation technology, the U.S. military, identifies unrealistic human and organizational behavior as a major limitation of existing simulation technology (NRC, 1998). And of course the entertainment industry has long recognized the importance of good character, emotional attachment and rich social interactions to "put butts in seats." This article describes a research effort to endow virtual training environments with richer models of social behavior. We have been developing autonomous and semi-autonomous software agents that plan and act while situated in a social network of other entities, human and synthetic (Hill et. al, 1997; Tambe, 1997; Gratch and Hill, 1999). My work has focused on making agents act in an organization and obey social constraints, coordinate their behavior, negotiate conflicts, but also obey their own self-interest and show a range of individual differences in their behavior and willingness to violate social norms, albeit within the relatively narrow context of a specific training exercise.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {incollection}
}
Bharitkar, Sunil; Kyriakakis, Chris
Eigenfilters for Signal Cancellation Proceedings Article
In: International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Hawaii, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{bharitkar_eigenfilters_2000,
title = {Eigenfilters for Signal Cancellation},
author = {Sunil Bharitkar and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/EIGENFILTERS%20FOR%20SIGNAL%20CANCELLATION.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)},
address = {Hawaii},
abstract = {Selectively canceling signals at specific locations within an acoustical environment with multiple listeners is of significant importance for home theater, automobile, teleconferencing, office, industrial and other applications. The traditional noise cancellation approach is impractical for such applications because it requires sensors that must be placed on the listeners. In this paper we investigate the theoretical properties of eigenfilters for signal cancellation proposed in [1]. We also investigate the sensitivity of the eigenfilter as a function of the room impulse response duration. Our results show that with the minimum phase model for the room impulse response, we obtain a better behaviour in the sensitivity of the filter to the duration of the room response.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Srinivasamurthy, Naveen; Ortega, Antonio; Narayanan, Shrikanth
Efficient Scalable Speech Compression for Scalable Speech Recognition Proceedings Article
In: Proceedings of the IEEE Conference on Multimedia and Expo, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{srinivasamurthy_efficient_2000,
title = {Efficient Scalable Speech Compression for Scalable Speech Recognition},
author = {Naveen Srinivasamurthy and Antonio Ortega and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Efficient%20Scalable%20Speech%20Compression%20for%20Scalable%20Speech%20Recognition.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the IEEE Conference on Multimedia and Expo},
abstract = {We propose a scalable recognition system for reducing recognition complexity. Scalable recognition can be combined with scalable compression in a distributed speech recognition (DSR) application to reduce both the computational load and the bandwidth requirement at the server. A low complexity preprocessor is used to eliminate the unlikely classes so that the complex recognizer can use the reduced subset of classes to recognize the unknown utterance. It is shown that by using our system it is fairly straightforward to trade-off reductions in complexity for performance degradation. Results of preliminary experiments using the TI-46 word digit database show that the proposed scalable approach can provide a 40% speed up, while operating under 1.05 kbps, compared to the baseline recognition using uncompressed speech.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1999
Georgiou, Panayiotis G.; Tsakalides, Panagiotis; Kyriakakis, Chris
Alpha-Stable Modeling of Noise and Robust Time- Delay Estimation in the Presence of Impulsive Noise Proceedings Article
In: IEEE Transactions on Multimedia, pp. 291–301, 1999.
Abstract | Links | BibTeX | Tags:
@inproceedings{georgiou_alpha-stable_1999,
title = {Alpha-Stable Modeling of Noise and Robust Time- Delay Estimation in the Presence of Impulsive Noise},
author = {Panayiotis G. Georgiou and Panagiotis Tsakalides and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/Alpha-Stable%20Modeling%20of%20Noise%20and%20Robust%20Time-%20Delay%20Estimation%20in%20the%20Presence%20of%20Impulsive%20Noise.pdf},
year = {1999},
date = {1999-09-01},
booktitle = {IEEE Transactions on Multimedia},
volume = {1},
pages = {291–301},
abstract = {A new representation of audio noise signals is proposed, based on symmetric-stable (S S) distributions in order to better model the outliers that exist in real signals. This representation addresses a shortcoming of the Gaussian model, namely, the fact that it is not well suited for describing signals with impulsive behavior. The stable and Gaussian methods are used to model measured noise signals. It is demonstrated that the stable distribution, which has heavier tails than the Gaussian distribution, gives a much better approximation to real-world audio signals. The significance of these results is shown by considering the time delay estimation (TDE) problem for source localization in teleimmersion applications. In order to achieve robust sound source localization, a novel time delay estimation approach is proposed. It is based on fractional lower order statistics (FLOS), which mitigate the effects of heavy-tailed noise. An improvement in TDE performance is demonstrated using FLOS that is up to a factor of four better than what can be achieved with second-order statistics.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Hill, Randall W.
Continuous Planning and Collaboration for Command and Control in Joint Synthetic Battlespaces Proceedings Article
In: Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation, Orlando, FL, 1999.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{gratch_continuous_1999,
title = {Continuous Planning and Collaboration for Command and Control in Joint Synthetic Battlespaces},
author = {Jonathan Gratch and Randall W. Hill},
url = {http://ict.usc.edu/pubs/Continuous%20Planning%20and%20Collaboration%20for%20Command%20and%20Control%20in%20Joint%20Synthetic%20Battlespaces.pdf},
year = {1999},
date = {1999-05-01},
booktitle = {Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation},
address = {Orlando, FL},
abstract = {In this paper we describe our efforts to model command and control entities for Joint Synthetic Battlespaces. Command agents require a broader repertoire of capabilities than is typically modeled in simulation. They must develop mission plans involving multiple subordinate units, monitor execution, dynamically modify mission plans in response to situational contingencies, collaborate with other decision makers, and deal with a host of organizational issues. We describe our approach to command agent modeling that addresses a number of these issues through its continuous and collaborative approach to mission planning.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Marsella, Stacy C.; Hill, Randall W.; III, LTC George Stone
Deriving Priority Intelligence Requirements for Synthetic Command Entities Proceedings Article
In: Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation, Orlando, FL, 1999.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{gratch_deriving_1999,
title = {Deriving Priority Intelligence Requirements for Synthetic Command Entities},
author = {Jonathan Gratch and Stacy C. Marsella and Randall W. Hill and LTC George Stone III},
url = {http://ict.usc.edu/pubs/Deriving%20Priority%20Intelligence%20Requirements%20for%20Synthetic%20Command%20Entities.pdf},
year = {1999},
date = {1999-05-01},
booktitle = {Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation},
address = {Orlando, FL},
abstract = {Simulation-based training is using increasingly complex synthetic forces. As more complex multiechelon synthetic forces are employed in simulations, the need for a realistic model of their command and control behavior becomes more urgent. In this paper we discuss one key component of such a model, the autonomous generation and use of priority intelligence requirements within multi-echelon plans.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Kyriakakis, Chris; Tsakalides, Panagiotis; Holman, Tomlinson
Surrounded by Sound: Acquisition and Rendering Methods for Immersive Audio Journal Article
In: Signal Processing Magazine, IEEE, vol. 16, no. 1, pp. 55–66, 1999, ISSN: 1053-5888.
Abstract | Links | BibTeX | Tags:
@article{kyriakakis_surrounded_1999,
title = {Surrounded by Sound: Acquisition and Rendering Methods for Immersive Audio},
author = {Chris Kyriakakis and Panagiotis Tsakalides and Tomlinson Holman},
url = {http://ict.usc.edu/pubs/Surrounded%20by%20Sound-%20Acquisition%20and%20Rendering%20Methods%20for%20Immersive%20Audio.pdf},
doi = {10.1109/79.743868},
issn = {1053-5888},
year = {1999},
date = {1999-01-01},
journal = {Signal Processing Magazine, IEEE},
volume = {16},
number = {1},
pages = {55–66},
abstract = {The authors discuss immersive audio systems and the signal processing issues that pertain to the acquisition and subsequent rendering of 3D sound fields over loudspeakers. On the acquisition side, recent advances in statistical methods for achieving acoustical arrays in audio applications are reviewed. Classical array signal processing addresses two major aspects of spatial filtering, namely localization of a signal of interest, and adaptation of the spatial response of an array of sensors to achieve steering in a given direction. The achieved spatial focusing in the direction of interest makes array signal processing a necessary component in immersive sound acquisition systems. On the rendering side, 3D audio signal processing methods are described that allow rendering of virtual sources around the listener using only two loudspeakers. Finally, the authors discuss the commercial implications of audio DSP.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Traum, David; Andersen, Carl F.; Chong, Waiyian; Josyula, Darsana; Okamoto, Yoshi; Purang, Khemdut; O'Donovan-Anderson, Michael; Perlis, Don
Representations of Dialogue State for Domain and Task Independent Meta-Dialogue Journal Article
In: Electronic Transactions on Artificial Intelligence, vol. 3, pp. 125–152, 1999.
Abstract | Links | BibTeX | Tags: Virtual Humans
@article{traum_representations_1999,
title = {Representations of Dialogue State for Domain and Task Independent Meta-Dialogue},
author = {David Traum and Carl F. Andersen and Waiyian Chong and Darsana Josyula and Yoshi Okamoto and Khemdut Purang and Michael O'Donovan-Anderson and Don Perlis},
url = {http://ict.usc.edu/pubs/Representations%20of%20Dialogue%20State%20for%20Domain%20and%20Task%20Independent%20Meta-Dialogue.pdf},
year = {1999},
date = {1999-01-01},
journal = {Electronic Transactions on Artificial Intelligence},
volume = {3},
pages = {125–152},
abstract = {We propose a representation of local dialogue context motivated by the need to react appropriately to meta-dialogue, such as various sorts of corrections to the sequence of an instruction and response action. Such contexts includes at least the following aspects: the words and linguistic structures uttered, the domain correlates of those linguistic structures, and plans and actions in response. Each of these is needed as part of the context in order to be able to correctly interpret the range of possible corrections. Partitioning knowledge of dialogue structure in this way may lead to an ability to represent generic dialogue structure (e.g., in the form of axioms), which can be particularized to the domain, topic and content of the dialogue.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Gratch, Jonathan
Why You Should Buy an Emotional Planner Proceedings Article
In: Proceedings of the Agents '99 Workshop on Emotion-Based Agent Architectures, 1999.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_why_1999,
title = {Why You Should Buy an Emotional Planner},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Why%20You%20Should%20Buy%20an%20Emotional%20Planner.pdf},
year = {1999},
date = {1999-01-01},
booktitle = {Proceedings of the Agents '99 Workshop on Emotion-Based Agent Architectures},
abstract = {Computation models of emotion have begun to address the problem of how agents arrive at a given emotional state, and how that state might alter their reactions to the environment. Existing work has focused on reactive models of behavior and does not, as of yet, provide much insight on how emotion might relate to the construction and execution of complex plans. This article focuses on this later question. I present a model of how agents ap- praise the emotion significance of events that illustrates a complementary relationship between classical planning methods and models of emotion processing. By building on classical planning methods, the model clarifies prior accounts of emotional appraisal and extends these ac- counts to handle the generation and execution of com- plex multi-agent plans.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
0369
Bosnak, Robert E.; Bosnak, David E.; Rizzo, Albert
Systems and methods for ai driven generation of content attuned to a user Patent
US20240005583A1, 0369.
Abstract | Links | BibTeX | Tags:
@patent{bosnak_systems_369,
title = {Systems and methods for ai driven generation of content attuned to a user},
author = {Robert E. Bosnak and David E. Bosnak and Albert Rizzo},
url = {https://patentimages.storage.googleapis.com/2a/a6/76/2607333241cd11/US20240005583A1.pdf},
year = {0369},
date = {0369-01-01},
number = {US20240005583A1},
abstract = {Systems and methods enabling rendering an avatar attuned to a user. The systems and methods include receiving audio-visual data of user communications of a user. Using the audio-visual data, the systems and methods may determine vocal characteristics of the user, facial action units representative of facial features of the user, and speech of the user based on a speech recognition model and/or natural language understanding model. Based on the vocal characteristics, an acoustic emotion metric can be determined. Based on the speech recognition data, a speech emotion metric may be determined. Based on the facial action units, a facial emotion metric may be determined. An emotional complex signature may be determined to represent an emotional state of the user for rendering the avatar attuned to the emotional state based on a combination of the acoustic emotion metric, the speech emotion metric and the facial emotion metric.},
keywords = {},
pubstate = {published},
tppubtype = {patent}
}
0000
[No title] Journal Article
In: 0000.
BibTeX | Tags: Learning Sciences, LLM
@article{nokey,
title = {[No title]},
keywords = {Learning Sciences, LLM},
pubstate = {published},
tppubtype = {article}
}
Bosnak, David E.; Bosnak, Robert E.; Rizzo, Albert
US11798217B2, 0000.
Abstract | Links | BibTeX | Tags:
@patent{bosnak_systems_nodate,
title = {Systems and methods for automated real-time generation of an interactive avatar utilizing short-term and long-term computer memory structures},
author = {David E. Bosnak and Robert E. Bosnak and Albert Rizzo},
url = {https://patentimages.storage.googleapis.com/8f/a5/ad/3e30e0837c20ee/US11798217.pdf},
number = {US11798217B2},
abstract = {Systems and methods enabling rendering an avatar attuned to a user. The systems and methods include receiving audio-visual data of user communications of a user. Using the audio-visual data, the systems and methods may determine vocal characteristics of the user, facial action units representative of facial features of the user, and speech of the user based on a speech recognition model and/or natural language understanding model. Based on the vocal characteristics, an acoustic emotion metric can be determined. Based on the speech recognition data, a speech emotion metric may be determined. Based on the facial action units, a facial emotion metric may be determined. An emotional complex signature may be determined to represent an emotional state of the user for rendering the avatar attuned to the emotional state based on a combination of the acoustic emotion metric, the speech emotion metric and the facial emotion metric.},
keywords = {},
pubstate = {published},
tppubtype = {patent}
}
Gratch, Jonathan
Emotion recognition ≠ Emotion Understanding: Challenges Confronting the Field of Affective Computing Journal Article
In: pp. 9, 0000.
BibTeX | Tags: Emotions, Virtual Humans
@article{gratch_emotion_nodate,
title = {Emotion recognition ≠ Emotion Understanding: Challenges Confronting the Field of Affective Computing},
author = {Jonathan Gratch},
pages = {9},
keywords = {Emotions, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Gervits, Felix; Leuski, Anton; Bonial, Claire; Gordon, Carla; Traum, David
A Classification-Based Approach to Automating Human-Robot Dialogue Journal Article
In: pp. 13, 0000.
Abstract | Links | BibTeX | Tags: ARL, Dialogue, UARC, Virtual Humans
@article{gervits_classication-based_nodate,
title = {A Classification-Based Approach to Automating Human-Robot Dialogue},
author = {Felix Gervits and Anton Leuski and Claire Bonial and Carla Gordon and David Traum},
url = {https://link.springer.com/chapter/10.1007/978-981-15-9323-9_10},
doi = {https://doi.org/10.1007/978-981-15-9323-9_10},
pages = {13},
abstract = {We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue including two wizards: one standing in for dialogue capabilities and another for navigation. Below, we describe the implementation details of the classifier and show how it was used to automate the dialogue wizard. We evaluate our system on several sets of source data from the corpus and find that response accuracy is generally high, even with very limited training data. Another contribution of this work is the novel demonstration of a dialogue manager that uses the classifier to engage in multifloor dialogue with two different human roles. Overall, this approach is useful for enabling spoken dialogue systems to produce robust and accurate responses to natural language input, and for robots that need to interact with humans in a team setting.},
keywords = {ARL, Dialogue, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; McCullough, Kyle; Mozgai, Sharon; Ustun, Volkan; Gordon, Andrew S
Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment Journal Article
In: pp. 11, 0000.
@article{hartholt_introducing_nodate,
title = {Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment},
author = {Arno Hartholt and Kyle McCullough and Sharon Mozgai and Volkan Ustun and Andrew S Gordon},
pages = {11},
abstract = {This paper describes the design, development, and philosophy of the Rapid Integration & Development Environment (RIDE). RIDE is a simulation platform that unites many Department of Defense (DoD) and Army simulation efforts to provide an accelerated development foundation and prototyping sandbox that provides direct benefit to the U.S. Army’s Synthetic Training Environment (STE) as well as the larger DoD and Army simulation communities. RIDE integrates a range of capabilities, including One World Terrain, Non-Player Character AI behaviors, xAPI logging, multiplayer networking, scenario creation, destructibility, machine learning approaches, and multi-platform support. The goal of RIDE is to create a simple, drag-and-drop development environment usable by people across all technical levels. RIDE leverages robust game engine technology while designed to be agnostic to any specific game or simulation engine. It provides decision makers with the tools needed to better define requirements and identify potential solutions in much less time and at much reduced costs. RIDE is available through Government Purpose Rights. We aim for RIDE to lower the barrier of entry to research and development efforts within the simulation community in order to reduce required time and effort for simulation and training prototyping. This paper provides an overview of our objective, overall approach, and next steps, in pursuit of these goals.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; McCullough, Kyle; Mozgai, Sharon; Ustun, Volkan; Gordon, Andrew S
Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment Journal Article
In: pp. 11, 0000.
@article{hartholt_introducing_nodate-1,
title = {Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment},
author = {Arno Hartholt and Kyle McCullough and Sharon Mozgai and Volkan Ustun and Andrew S Gordon},
pages = {11},
abstract = {This paper describes the design, development, and philosophy of the Rapid Integration & Development Environment (RIDE). RIDE is a simulation platform that unites many Department of Defense (DoD) and Army simulation efforts to provide an accelerated development foundation and prototyping sandbox that provides direct benefit to the U.S. Army’s Synthetic Training Environment (STE) as well as the larger DoD and Army simulation communities. RIDE integrates a range of capabilities, including One World Terrain, Non-Player Character AI behaviors, xAPI logging, multiplayer networking, scenario creation, destructibility, machine learning approaches, and multi-platform support. The goal of RIDE is to create a simple, drag-and-drop development environment usable by people across all technical levels. RIDE leverages robust game engine technology while designed to be agnostic to any specific game or simulation engine. It provides decision makers with the tools needed to better define requirements and identify potential solutions in much less time and at much reduced costs. RIDE is available through Government Purpose Rights. We aim for RIDE to lower the barrier of entry to research and development efforts within the simulation community in order to reduce required time and effort for simulation and training prototyping. This paper provides an overview of our objective, overall approach, and next steps, in pursuit of these goals.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; Mozgai, Sharon
From Combat to COVID-19 – Managing the Impact of Trauma Using Virtual Reality Journal Article
In: pp. 35, 0000.
Abstract | BibTeX | Tags: DTIC, MedVR, Virtual Humans, VR
@article{hartholt_combat_nodate,
title = {From Combat to COVID-19 – Managing the Impact of Trauma Using Virtual Reality},
author = {Arno Hartholt and Sharon Mozgai},
pages = {35},
abstract = {Research has documented the efficacy of clinical applications that leverage Virtual Reality (VR) for assessment and treatment purposes across a wide range of domains, including pain, phobias, and posttraumatic stress disorder (PTSD). As the field of Clinical VR matures, it is important to review its origins and examine how these initial explorations have progressed, what gaps remain, and what opportunities the community can pursue. We do this by reflecting on our personal scientific journey against the backdrop of the field in general. In particular, this paper discusses how a clinical research program that was initially designed to deliver trauma-focused VR exposure therapy (VRET) for combat-related PTSD has been evolved to expand its impact and address a wider range of trauma sources. Such trauma sources include sexual trauma and the needs of first responders and healthcare professionals serving on the frontlines of the COVID-19 pandemic. We provide an overview of the field and its general trends, discuss the genesis of our research agenda and its current status, and summarize upcoming opportunities, together with common challenges and lessons learned.},
keywords = {DTIC, MedVR, Virtual Humans, VR},
pubstate = {published},
tppubtype = {article}
}
The Interservice Industry, Training, Simulation, and Education Conference Miscellaneous
0000.
@misc{noauthor_interservice_nodate,
title = {The Interservice Industry, Training, Simulation, and Education Conference},
url = {https://www.xcdsystem.com/iitsec/proceedings/index.cfm?Year=2021&AbID=97189&CID=862},
urldate = {2022-09-22},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
APA PsycNet Miscellaneous
0000.
@misc{noauthor_apa_nodate,
title = {APA PsycNet},
url = {https://psycnet.apa.org/fulltext/2022-19957-001.html},
urldate = {2022-09-13},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Chen, Haiwei; Zhao, Yajie
Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting Proceedings Article
In: pp. 7591–7600, 0000.
Abstract | Links | BibTeX | Tags: DTIC, Graphics, VGL
@inproceedings{chen_dont_nodate,
title = {Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting},
author = {Haiwei Chen and Yajie Zhao},
url = {https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Dont_Look_into_the_Dark_Latent_Codes_for_Pluralistic_Image_CVPR_2024_paper.html},
pages = {7591–7600},
abstract = {We present a method for large-mask pluralistic image inpainting based on the generative framework of discrete latent codes. Our method learns latent priors discretized as tokens by only performing computations at the visible locations of the image. This is realized by a restrictive partial encoder that predicts the token label for each visible block a bidirectional transformer that infers the missing labels by only looking at these tokens and a dedicated synthesis network that couples the tokens with the partial image priors to generate coherent and pluralistic complete image even under extreme mask settings. Experiments on public benchmarks validate our design choices as the proposed method outperforms strong baselines in both visual quality and diversity metrics.},
keywords = {DTIC, Graphics, VGL},
pubstate = {published},
tppubtype = {inproceedings}
}
Artstein, Ron; Chen, Elizabeth
Augmenting Training Data for a Virtual Character Using GPT-3.5 Proceedings Article
In: Tyhe Florida Artificial Intelligence Research Society, 0000.
Abstract | Links | BibTeX | Tags: Dialogue, DTIC, Natural Language
@inproceedings{artstein_augmenting_nodate,
title = {Augmenting Training Data for a Virtual Character Using GPT-3.5},
author = {Ron Artstein and Elizabeth Chen},
url = {https://journals.flvc.org/FLAIRS/article/view/135552},
volume = {37},
publisher = {Tyhe Florida Artificial Intelligence Research Society},
abstract = {This paper compares different methods of using a large lan-guage model (GPT-3.5) for creating synthetic training datafor a retrieval-based conversational character. The trainingdata are in the form of linked questions and answers, whichallow a classifier to retrieve a pre-recorded answer to an un-seen question; the intuition is that a large language modelcould predict what human users might ask, thus saving theeffort of collecting real user questions as training data. Re-sults show small improvements in test performance for allsynthetic datasets. However, a classifier trained on only smallamounts of collected user data resulted in a higher F-scorethan the classifiers trained on much larger amounts of syn-thetic data generated using GPT-3.5. Based on these results,we see a potential in using large language models for gener-ating training data, but at this point it is not as valuable ascollecting actual user data for training.},
keywords = {Dialogue, DTIC, Natural Language},
pubstate = {published},
tppubtype = {inproceedings}
}
Mozgai, Sharon; Rizzo, Albert A; Hartholt, Arno
Persuasive Technology for Suicide Prevention: A Virtual Human mHealth Application Proceedings Article
In: 0000.
Abstract | BibTeX | Tags: Virtual Humans, VR
@inproceedings{mozgai_persuasive_nodate,
title = {Persuasive Technology for Suicide Prevention: A Virtual Human mHealth Application},
author = {Sharon Mozgai and Albert A Rizzo and Arno Hartholt},
abstract = {We are demoing Battle Buddy, an mHealth application designed to support access to physical and mental wellness content as well as safety planning for U.S. military veterans. This virtual human interface will collect multimodal data through passive sensors native to popular wearables (e.g., Apple Watch) and deliver adaptive multimedia content specifically tailored to the user in the interdependent domains of physical, cognitive, and emotional health. Battle Buddy can deliver health interventions matched to the individual user via novel adaptive logic-based algorithms while employing various behavior change techniques (e.g., goal-setting, barrier identification, rewards, modeling, etc.). All interactions were specifically designed to engage and motivate by employing the persuasive strategies of (1) personalization, (2) self-monitoring, (3) tunneling, (4) suggestion, and (5) expertise.},
keywords = {Virtual Humans, VR},
pubstate = {published},
tppubtype = {inproceedings}
}