Publications
Search
Chatterjee, Moitreya; Leuski, Anton
CRMActive: An Active Learning Based Approach for Effective Video Annotation and Retrieval Proceedings Article
In: Proceedings of ACM International Conference on Multimedia Retrieval (ICMR), pp. 535–538, ACM, Shanghai, China, 2015.
@inproceedings{chatterjee_crmactive_2015,
title = {CRMActive: An Active Learning Based Approach for Effective Video Annotation and Retrieval},
author = {Moitreya Chatterjee and Anton Leuski},
url = {http://ict.usc.edu/pubs/CRMActive%20-%20An%20Active%20Learning%20Based%20Approach%20for%20Effective%20Video%20Annotation%20and%20Retrieval.pdf},
doi = {10.1145/2671188.2749342},
year = {2015},
date = {2015-06-01},
booktitle = {Proceedings of ACM International Conference on Multimedia Retrieval (ICMR)},
pages = {535–538},
publisher = {ACM},
address = {Shanghai, China},
abstract = {Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [7]require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the training data, allows for a good performance even before the training data is fully annotated. In this work we propose an active learning algorithm, which combines a novel measure of sample uncertainty with a novel clustering-based approach for determining sample density and diversity and integrate it with NormCRM. The clusters are also iteratively re⬚ned to ensure both feature and label-level agreement among samples. We show that our approach outperforms multiple baselines both on a new, open dataset and on the popular TRECVID corpus at both the tasks of annotation and text-based retrieval of videos.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nye, Benjamin D.; Goldberg, Ben; Hu, Xiangen
Generalizing the Genres for ITS: Authoring Considerations for Representative Learning Tasks Book Section
In: Sottilare, Robert A.; Graesser, Arthur C.; Hu, Xiangen; Brawner, Keith (Ed.): Design Recommendations for Intelligent Tutoring Systems: Volume 2: Authoring Tools and Expert Modeling Techniques, vol. 3, pp. 47–63, U.S. Army Research Laboratory, 2015, ISBN: 978-0-9893923-7-2.
@incollection{nye_generalizing_2015,
title = {Generalizing the Genres for ITS: Authoring Considerations for Representative Learning Tasks},
author = {Benjamin D. Nye and Ben Goldberg and Xiangen Hu},
editor = {Robert A. Sottilare and Arthur C. Graesser and Xiangen Hu and Keith Brawner},
url = {http://ict.usc.edu/pubs/Generalizing%20the%20Genres%20for%20ITS%20-%20Authoring%20Considerations%20for%20Representative%20Learning%20Tasks.pdf},
isbn = {978-0-9893923-7-2},
year = {2015},
date = {2015-06-01},
booktitle = {Design Recommendations for Intelligent Tutoring Systems: Volume 2: Authoring Tools and Expert Modeling Techniques},
volume = {3},
pages = {47–63},
publisher = {U.S. Army Research Laboratory},
abstract = {Compared to many other learning technologies, intelligent tutoring systems (ITSs) have a distinct challenge: authoring an adaptive inner loop that provides pedagogical support on one or more learning tasks. This coupling of tutoring behavior to student interaction with a learning task means that authoring tools need to reflect both the learning task and the ITS pedagogy. To explore this issue, common learning activities in intelligent tutoring need to be categorized and analyzed for the information that is required to tutor each task. The types of learning activities considered cover a large range: step-by-step problem solving, bug repair, building generative functions (e.g., computer code), structured argumentation, self-reflection, short question answering, essay writing, classification, semantic matching, representation mapping (e.g., graph to equation), concept map revision, choice scenarios, simulated process scenarios, motor skills practice, collaborative discussion, collaborative design, and team coordination tasks. These different tasks imply a need for different authoring tools and processes used to create tutoring systems for each task. In this chapter, we consider three facets of authoring: 1) the minimum information required to create the task, 2) the minimum information needed to implement common pedagogical strategies, 3) the expertise required for each type of information. The goal of this analysis is to present a roadmap of effective practices in authoring tool interfaces for each tutoring task considered. A long-term vision for ITSs is to have generalizable authoring tools, which could be used to rapidly create content for a variety of ITSs. However, it is as-yet unclear if this goal is even attainable. Authoring tools have a number of serious challenges, from the standpoint of generalizability. These challenges include the domain, the data format, and the author. First, different ITS domains require different sets of authoring tools, because they have different learning tasks. Tools that are convenient for embedding tutoring in a 3D virtual world are completely different than ones that make it convenient to add tutoring to a system for practicing essay-writing, for example. Second, the data produced by an authoring tool needs to be consumed by an ITS that will make pedagogical decisions. As such, at least some of the data is specific to the pedagogy of the ITS, rather than directly reflecting domain content. As a simple example, if an ITS uses text hints, those hints need to be authored, but some systems may just highlight errors rather than providing text hints. As such, the first system actually needs more content authored and represented as data. With that said, typical ITSs use a relatively small and uniform set of authored content to interact with learners, such as correctness feedback, corrections, and hints (VanLehn, 2006). Third, different authors may need different tools (Nye, Rahman, Yang, Hays, Cai, Graesser, & Hu, 2014). This means that even the same content may need distinct authoring tools that match the expertise of different authors. In this chapter, we are focusing primarily on the first challenge: differences in domains. In particular, our stance is that the “content domain” is too coarse-grained to allow much reuse between authoring tools. This is because, to a significant extent, content domains are simply names for related content. However, the skills and pedagogy for the same domain can vary drastically across different topics and expertise levels. For example, Algebra and Geometry are both high-school level math domains. However, in geometry, graphical depictions (e.g., shapes, angles) are a central aspect of the pedagogy, while Algebra tends to use graphics very differently (e.g., coordinate plots). As such, some learning tasks tend to be shared between those subdomains (e.g., equation-solving) and other tasks are not (e.g., classifying shapes). This raises the central point of our paper: the learning tasks for a domain define how we author content for that domain. For example, while Algebra does not involve recognizing many shapes, understanding the elements of architecture involves recognizing a variety of basic and advanced shapes and forms. In total, this means that no single whole-cloth authoring tool will work well for any pair of Algebra, Geometry, and Architectural Forms. However, it also implies that a reasonable number of task-specific tools for each learning task might allow authoring for all three domains. To do this, we need to understand the common learning tasks for domains taught using ITS, and why those tasks are applied to those domains. In the following sections, we identify and categorize common learning tasks for different ITS domains. Then, we extract common principles for those learning tasks. Finally, we suggest a set of general learning activities that might be used to tutor a large number of domains.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Nye, Benjamin D.; Hu, Xiangen
A Historical Perspective on Authoring and ITS: Reviewing Some Lessons Learned Book Section
In: Sottilare, Robert A.; Graesser, Arthur C.; Hu, Xiangen; Brawner, Keith (Ed.): Design Recommendations for Intelligent Tutoring Systems: Volume 2: Authoring Tools and Expert Modeling Techniques, pp. 67–70, U.S. Army Research Laboratory, 2015, ISBN: 978-0-9893923-7-2.
@incollection{nye_historical_2015,
title = {A Historical Perspective on Authoring and ITS: Reviewing Some Lessons Learned},
author = {Benjamin D. Nye and Xiangen Hu},
editor = {Robert A. Sottilare and Arthur C. Graesser and Xiangen Hu and Keith Brawner},
url = {http://ict.usc.edu/pubs/A%20Historical%20Perspective%20on%20Authoring%20and%20ITS%20-%20Reviewing%20Some%20Lessons%20Learned.pdf},
isbn = {978-0-9893923-7-2},
year = {2015},
date = {2015-06-01},
booktitle = {Design Recommendations for Intelligent Tutoring Systems: Volume 2: Authoring Tools and Expert Modeling Techniques},
pages = {67–70},
publisher = {U.S. Army Research Laboratory},
abstract = {This section discusses the practices and lessons learned from authoring tools that have been applied and revised through repeated use by researchers, content authors, and/or instructors. All of the tools noted in this section represent relatively mature applications that can be used to build and configure educationally-effective content. Each tool has been tailored to address both the tutoring content and the expected authors who will be using the tool. As such, even tools which support similar tutoring strategies may use very different interfaces to represent equivalent domain knowledge. In some cases, authoring tools even represent offshoots where different authoring goals led to divergent evolution of both the authoring tools and the intelligent tutoring systems (ITSs) from a common lineage. Understanding how these systems adapted their tools to their particular authoring challenges gives concrete examples of the tradeoffs involved for different types of authoring. By reviewing the successes and challenges of the past, these chapters provide lessons learned for the development of future systems.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Saito, Shunsuke; Huang, Zeng; Natsume, Ryota; Morishima, Shigeo; Kanazawa, Angjoo; Li, Hao
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization Journal Article
In: arXiv:1905.05172 [cs], 2015.
@article{saito_pifu_2015,
title = {PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization},
author = {Shunsuke Saito and Zeng Huang and Ryota Natsume and Shigeo Morishima and Angjoo Kanazawa and Hao Li},
url = {http://arxiv.org/abs/1905.05172},
year = {2015},
date = {2015-05-01},
journal = {arXiv:1905.05172 [cs]},
abstract = {We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object. Using PIFu, we propose an end-to-end deep learning method for digitizing highly detailed clothed humans that can infer both 3D surface and texture from a single image, and optionally, multiple input images. Highly intricate shapes, such as hairstyles, clothing, as well as their variations and deformations can be digitized in a unified way. Compared to existing representations used for 3D deep learning, PIFu can produce high-resolution surfaces including largely unseen regions such as the back of a person. In particular, it is memory efficient unlike the voxel representation, can handle arbitrary topology, and the resulting surface is spatially aligned with the input image. Furthermore, while previous techniques are designed to process either a single image or multiple views, PIFu extends naturally to arbitrary number of views. We demonstrate high-resolution and robust reconstructions on real world images from the DeepFashion dataset, which contains a variety of challenging clothing types. Our method achieves state-of-the-art performance on a public benchmark and outperforms the prior work for clothed human digitization from a single image.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Artstein, Ron; Leuski, Anton; Maio, Heather; Mor-Barak, Tomer; Gordon, Carla; Traum, David
How Many Utterances Are Needed to Support Time-Offset Interaction? Proceedings Article
In: Proceedings of FLAIRS 28, pp. 144–149, AAAI Press, Hollywood, FL, 2015, ISBN: 978-1-57735-730-8.
@inproceedings{artstein_how_2015,
title = {How Many Utterances Are Needed to Support Time-Offset Interaction?},
author = {Ron Artstein and Anton Leuski and Heather Maio and Tomer Mor-Barak and Carla Gordon and David Traum},
url = {http://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS15/paper/view/10442},
isbn = {978-1-57735-730-8},
year = {2015},
date = {2015-05-01},
booktitle = {Proceedings of FLAIRS 28},
pages = {144–149},
publisher = {AAAI Press},
address = {Hollywood, FL},
abstract = {A set of several hundred recorded statements by a single speaker is sufficient to address unrestricted questions and sustain short conversations on a circumscribed topic. Statements were recorded by Pinchas Gutter, a Holocaust survivor, talking about his personal experiences before, during and after the Holocaust. These statements were delivered to participants in conversation, using a “Wizard of Oz” system, where live operators select an appropriate reaction to each user utterance in real time. Even though participants were completely unconstrained in the questions they could ask, the recorded statements were able to directly address at least 58% of user questions. The unanswered questions were then analyzed to identify gaps, and additional statements were recorded to fill the gaps. The statements will be put in an automated system using existing language understanding technology, to create the first full working system of time-offset interaction, allowing a live conversation with a real human who is not present for the conversation in real time.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lucas, Gale M.; McCubbins, Mathew D.; Turner, Mark
Against Game Theory Book Section
In: Emerging Trends in the Social and Behavioral Sciences: An Interdisciplinary, Searchable, and Linkable Resource, pp. 1–16, John Wiley & Sons, Inc., Hoboken, NJ, 2015, ISBN: 978-1-118-90077-2.
@incollection{lucas_against_2015,
title = {Against Game Theory},
author = {Gale M. Lucas and Mathew D. McCubbins and Mark Turner},
url = {http://ict.usc.edu/pubs/Against%20GameTheory.pdf},
isbn = {978-1-118-90077-2},
year = {2015},
date = {2015-05-01},
booktitle = {Emerging Trends in the Social and Behavioral Sciences: An Interdisciplinary, Searchable, and Linkable Resource},
pages = {1–16},
publisher = {John Wiley & Sons, Inc.},
address = {Hoboken, NJ},
abstract = {People make choices. Often, the outcome depends on choices other people make. What mental steps do people go through when making such choices? Game theory, the most influential model of choice in economics and the social sciences, offers an answer, one based on games of strategy like chess and checkers: the chooser considers the choices that others will make and makes a choice that will lead to a better outcome for the chooser, given all those choices by other people. It is universally established in the social sciences that classical game theory (even when heavily modified) is bad at predicting behavior. But instead of abandoning classical game theory, those in the social sciences have mounted a rescue operation under the name of “behavioral game theory.” Its main tool is to propose systematic deviations from the predictions of game theory, deviations that arise from character type, for example. Other deviations purportedly come from cognitive overload or limitations. The fundamental idea of behavioral game theory is that, if we know the deviations, then we can correct our predictions accordingly, and so get it right. There are two problems with this rescue operation, each of them fatal. (1) For a chooser, contemplating the range of possible deviations, as there are many dozens, actually makes it exponentially harder to figure out a path to an outcome. This makes the theoretical models useless for modeling human thought or human behavior in general. (2) Modeling deviations is helpful only if the deviations are consistent, so that scientists (and indeed decision-makers) can make 2 predictions about future choices on the basis of past choices. But the deviations are not consistent. In general, deviations from classical models are not consistent for any individual from one task to the next or between individuals for the same task. In addition, people’s beliefs are in general not consistent with their choices. Accordingly, all hope is hollow that we can construct a general behavioral game theory. What can replace it? We survey some of the emerging candidates.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Rizzo, Albert; Cukor, Judith; Gerardi, Maryrose; Alley, Stephanie; Reist, Chris; Roy, Mike; Rothbaum, Barbara O.; Difede, JoAnn
Virtual Reality Exposure for PTSD Due to Military Combat and Terrorist Attacks Journal Article
In: Journal of Contemporary Psychotherapy, pp. 1 –10, 2015, ISSN: 0022-0116, 1573-3564.
@article{rizzo_virtual_2015,
title = {Virtual Reality Exposure for PTSD Due to Military Combat and Terrorist Attacks},
author = {Albert Rizzo and Judith Cukor and Maryrose Gerardi and Stephanie Alley and Chris Reist and Mike Roy and Barbara O. Rothbaum and JoAnn Difede},
url = {http://ict.usc.edu/pubs/Virtual%20Reality%20Exposure%20for%20PTSD%20Due%20to%20Military%20Combat%20and%20Terrorist%20Attacks.pdf},
doi = {10.1007/s10879-015-9306-3},
issn = {0022-0116, 1573-3564},
year = {2015},
date = {2015-05-01},
journal = {Journal of Contemporary Psychotherapy},
pages = {1 –10},
abstract = {Humans exposed to war and terrorist attacks are at risk for the development of posttraumatic stress disorder (PTSD). Numerous reports indicate that the incidence of PTSD in both returning Operation Enduring Freedom/Operation Iraqi Freedom (OEF/OIF) military personnel and survivors of the 9/11 World Trade Center (WTC) attacks is significant. These situations have served to motivate research on how to better develop and disseminate evidence-based treatments for PTSD and other related psychosocial conditions. Virtual reality (VR) delivered exposure therapy for PTSD is currently being used to treat combat and terrorist attack related PTSD with initial reports of positive outcomes. This paper presents an overview and rationale for the use of VR exposure therapy with anxiety disorders and PTSD and describes the status of two systems (Virtual Iraq/Afghanistan and Virtual World Trade Center) developed for this purpose.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mell, Johnathan; Lucas, Gale; Gratch, Jonathan
An Effective Conversation Tactic for Creating Value over Repeated Negotiations Proceedings Article
In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, pp. 1567–1576, International Foundation for Autonomous Agents and Multiagent Systems, Istanbul, Turkey, 2015.
@inproceedings{mell_effective_2015,
title = {An Effective Conversation Tactic for Creating Value over Repeated Negotiations},
author = {Johnathan Mell and Gale Lucas and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/An%20Effective%20Conversation%20Tactic%20for%20Creating%20Value%20over%20Repeated%20Negotiations.pdf},
year = {2015},
date = {2015-05-01},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems},
pages = {1567–1576},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Istanbul, Turkey},
abstract = {Automated negotiation research focuses on getting the most value from a single negotiation, yet real-world settings often involve repeated serial negotiations between the same parties. Repeated negotiations are interesting because they allow the discovery of mutually beneficial solutions that don’t exist within the confines of a single negotiation. This paper introduces the notion of Pareto efficiency over time to formalize this notion of value-creation through repeated interactions. We review literature from human negotiation research and identify a dialog strategy, favors and ledgers, that facilitates this process. As part of a longer-term effort to build intelligent virtual humans that can train human negotiators, we create a conversational agent that instantiates this strategy, and assess its effectiveness with human users, using the established Colored Trails negotiation testbed. In an empirical study involving a series of repeated negotiations, we show that humans are more likely to discover Pareto optimal solutions overtime when matched with our favor-seeking agent. Further, an agent that asks for favors during early negotiations, regardless of whether these favors are ever repaid, leads participants to discover more joint value in later negotiations, even under the traditional definition of Pareto optimality within a single negotiation. Further, agents that match their words with deeds (repay their favors) create the most value for themselves. We discuss the implications of these findings for agents that engage in long-term interactions with human users.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Ning; Pynadath, David V.; Marsella, Stacy C.
Subjective Perceptions in Wartime Negotiation Journal Article
In: IEEE Transactions on Affective Computing, vol. 6, no. 2, pp. 118–126, 2015, ISSN: 1949-3045.
@article{wang_subjective_2015,
title = {Subjective Perceptions in Wartime Negotiation},
author = {Ning Wang and David V. Pynadath and Stacy C. Marsella},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6975149},
doi = {10.1109/TAFFC.2014.2378312},
issn = {1949-3045},
year = {2015},
date = {2015-04-01},
journal = {IEEE Transactions on Affective Computing},
volume = {6},
number = {2},
pages = {118–126},
abstract = {The prevalence of negotiation in social interaction has motivated researchers to develop virtual agents that can understand, facilitate, teach and even carry out negotiations. While much of this research has analyzed how to maximize the objective outcome, there is a growing body of work demonstrating that subjective perceptions of the outcome also play a critical role in human negotiation behavior. People derive subjective value from not only the outcome, but also from the process by which they achieve that outcome, from their relationship with their negotiation partner, etc. The affective responses evoked by these subjective valuations can be very different from what would be evoked by the objective outcome alone. We investigate such subjective valuations within human-agent negotiation in four variations of a wartime negotiation game. We observe that the objective outcomes of these negotiations are not strongly correlated with the human negotiators’ subjective perceptions, as measured by the Subjective Value Index. We examine the game dynamics and agent behaviors to identify features that induce different subjective values in the participants. We thus are able to identify characteristics of the negotiation process and the agents’ behavior that most impact people’s subjective valuations in our wartime negotiation games.⬚},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fyffe, Graham; Debevec, Paul
Single-Shot Reflectance Measurement from Polarized Color Gradient Illumination Proceedings Article
In: Preceedings of ICCP 2015, pp. 1–10, IEEE, Houston, Texas, 2015.
@inproceedings{fyffe_single-shot_2015,
title = {Single-Shot Reflectance Measurement from Polarized Color Gradient Illumination},
author = {Graham Fyffe and Paul Debevec},
url = {http://ict.usc.edu/pubs/Single-Shot%20Reflectance%20Measurement%20from%20Polarized%20Color%20Gradient%20Illumination.pdf},
year = {2015},
date = {2015-04-01},
booktitle = {Preceedings of ICCP 2015},
pages = {1–10},
publisher = {IEEE},
address = {Houston, Texas},
abstract = {We present a method for acquiring the per-pixel diffuse albedo, specular albedo, and surface normal maps of a subject at a single instant in time. The method is single shot, requiring no optical flow, and per-pixel, making no assumptions regarding albedo statistics or surface connectivity. We photograph the subject inside a spherical illumination device emitting a static lighting pattern of vertically polarized RGB color gradients aligned with the XYZ axes, and horizontally polarized RGB color gradients in versely aligned with the XYZ axes. We capture simultaneous photographs using one of two possible setups: a single view setup using a coaxially aligned camera pair with a polarizing beam splitter, and a multi-view stereo setup with different orientations of linear polarizing filters placed on the cameras, enabling high-quality geometry reconstruction. From this lighting we derive full-color diffuse albedo, single-channel specular albedo suitable for dielectric materials, and polarization-preserving surface normals which are free of corruption from subsurface scattering. We provide simple formulae to estimate the diffuse albedo, specular albedo, and surface normal maps in the single-view and multi-view cases and show error bounds which are small for many common subjects including faces.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Shim, Han Suk; Park, Sunghyun; Chatterjee, Moitreya; Scherer, Stefan; Sagae, Kenji; Morency, Louis-Philippe
ACOUSTIC AND PARA-VERBAL INDICATORS OF PERSUASIVENESS IN SOCIAL MULTIMEDIA Proceedings Article
In: Proceeding of ICASSP 2015, pp. 2239 – 2243, IEEE, Brisbane, Australia, 2015.
@inproceedings{shim_acoustic_2015,
title = {ACOUSTIC AND PARA-VERBAL INDICATORS OF PERSUASIVENESS IN SOCIAL MULTIMEDIA},
author = {Han Suk Shim and Sunghyun Park and Moitreya Chatterjee and Stefan Scherer and Kenji Sagae and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/ACOUSTIC%20AND%20PARA-VERBAL%20INDICATORS%20OF%20PERSUASIVENESS%20IN%20SOCIAL%20MULTIMEDIA.pdf},
year = {2015},
date = {2015-04-01},
booktitle = {Proceeding of ICASSP 2015},
pages = {2239 – 2243},
publisher = {IEEE},
address = {Brisbane, Australia},
abstract = {Persuasive communication and interaction play an important and pervasive role in many aspects of our lives. With the rapid growth of social multimedia websites such as YouTube, it has become more important and useful to understand persuasiveness in the context of online social multimedia content. In this paper, we present our resultsof conducting various analyses of persuasiveness in speech with our multimedia corpus of 1,000 movie review videos obtained from ExpoTV.com, a popular social multimedia website. Our experiments firstly show that a speaker’s level of persuasiveness can be predicted from acoustic characteristics and para-verbal cues related to speech fluency. Secondly, we show that taking acoustic cues in different time periods of a movie review can improve the performance of predicting a speaker’s level of persuasiveness. Lastly, we show that a speaker’s positive or negative attitude toward a topic influences the prediction performance as well.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Scherer, Stefan; Morency, Louis-Philippe; Gratch, Jonathan; Pestian, John
REDUCED VOWEL SPACE IS A ROBUST INDICATOR OF PSYCHOLOGICAL DISTRESS: A CROSS-CORPUS ANALYSIS Proceedings Article
In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4789–4793, IEEE, Brisbane, Australia, 2015.
@inproceedings{scherer_reduced_2015,
title = {REDUCED VOWEL SPACE IS A ROBUST INDICATOR OF PSYCHOLOGICAL DISTRESS: A CROSS-CORPUS ANALYSIS},
author = {Stefan Scherer and Louis-Philippe Morency and Jonathan Gratch and John Pestian},
url = {http://ict.usc.edu/pubs/REDUCED%20VOWEL%20SPACE%20IS%20A%20ROBUST%20INDICATOR%20OF%20PSYCHOLOGICAL%20DISTRESS-A%20CROSS-CORPUS%20ANALYSIS.pdf},
year = {2015},
date = {2015-04-01},
booktitle = {Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
pages = {4789–4793},
publisher = {IEEE},
address = {Brisbane, Australia},
abstract = {Reduced frequency range in vowel production is a well documented speech characteristic of individuals’ with psychological and neurological disorders. Depression is known to influence motor control and in particular speech production. The assessment and documentation of reduced vowel space and associated perceived hypoarticulation and reduced expressivity often rely on subjective assessments. Within this work, we investigate an automatic unsupervised machine learning approach to assess a speaker’s vowel space within three distinct speech corpora and compare observed vowel space measures of subjects with and without psychological conditions associated with psychological distress, namely depression, post-traumatic stress disorder (PTSD), and suicidality. Our experiments are based on recordings of over 300 individuals. The experiments show a significantly reduced vowel space in conversational speech for depression, PTSD, and suicidality. We further observe a similar trend of reduced vowel space for read speech. A possible explanation for a reduced vowel space is psychomotor retardation, a common symptom of depression that influences motor control and speech production.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Andreatta, Pamela; Klotz, Jessica J.; Madsen, James M.; Hurst, Charles G.; Talbot, Thomas B.
Outcomes From Two Forms of Training for First-Responder Competency in Cholinergic Crisis Management Journal Article
In: Military Medicine, vol. 180, no. 4, pp. 468–474, 2015, ISSN: 0026-4075, 1930-613X.
@article{andreatta_outcomes_2015,
title = {Outcomes From Two Forms of Training for First-Responder Competency in Cholinergic Crisis Management},
author = {Pamela Andreatta and Jessica J. Klotz and James M. Madsen and Charles G. Hurst and Thomas B. Talbot},
url = {http://ict.usc.edu/pubs/Outcomes%20From%20Two%20Forms%20of%20Training%20for%20First-Responder%20Competency%20in%20Cholinergic%20Crisis%20Management.pdf},
doi = {10.7205/MILMED-D-14-00290},
issn = {0026-4075, 1930-613X},
year = {2015},
date = {2015-04-01},
journal = {Military Medicine},
volume = {180},
number = {4},
pages = {468–474},
abstract = {Military and civilian first responders must be able to recognize and effectively manage mass disaster casualties. Clinical management of injuries resulting from nerve agents provides different challenges for first responders than those of conventional weapons. We evaluated the impact of a mixed-methods training program on competency acquisition in cholinergic crisis clinical management using multimedia with either live animal or patient actor examples, and hands-on practice using SimMan3G mannequin simulators. A purposively selected sample of 204 civilian and military first responders who had not previously completed nerve agent training were assessed pre- and post-training for knowledge, performance, self-efficacy, and affective state. We conducted analysis of variance with repeated measures; statistical significance p textbackslashtextbackslashtextless 0.05. Both groups had significant performance improvement across all assessment dimensions: knowledge textbackslashtextbackslashtextgreater 20%, performance textbackslashtextbackslashtextgreater 50%, self-efficacy textbackslashtextbackslashtextgreater 34%, and affective state textbackslashtextbackslashtextgreater 15%. There were no significant differences between the live animal and patient actor groups. These findings could aid in the specification of training for first-responder personnel in military and civilian service. Although less comprehensive than U.S. Army Medical Research Institute of Chemical Defense courses, the training outcomes associated with this easily distributed program demonstrate its value in increasing the competency of first responders in recognizing and managing a mass casualty cholinergic event.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rosenbloom, Paul
Supraarchitectural Capability Integration: From Soar to Sigma Proceedings Article
In: Proceedings of the 13th International Conference on Cognitive Modeling, 2015, Groningen, The Netherlands, 2015.
@inproceedings{rosenbloom_supraarchitectural_2015,
title = {Supraarchitectural Capability Integration: From Soar to Sigma},
author = {Paul Rosenbloom},
url = {http://ict.usc.edu/pubs/Supraarchitectural%20Capability%20Integration%20-%20From%20Soar%20to%20Sigma.pdf},
year = {2015},
date = {2015-04-01},
booktitle = {Proceedings of the 13th International Conference on Cognitive Modeling, 2015},
address = {Groningen, The Netherlands},
abstract = {Integration across capabilities, both architectural and supraarchitectural, is critical for cognitive architectures. Here we revisit a classic failure of supraarchitectural capability integration in Soar, involving data chunking, to understand better both its source and how it and related integration issues can be overcome via three general extensions in Sigma.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Suma, Evan A.; Krum, David M.; Richmond, Todd; Bolas, Mark
The MxR Lab at the USC Institute for Creative Technologies Book
Arles, France, 2015.
@book{suma_mxr_2015,
title = {The MxR Lab at the USC Institute for Creative Technologies},
author = {Evan A. Suma and David M. Krum and Todd Richmond and Mark Bolas},
url = {http://ict.usc.edu/pubs/The%20MxR%20Lab%20at%20the%20USC%20Institute%20for%20Creative%20Technologies.pdf},
year = {2015},
date = {2015-03-01},
address = {Arles, France},
abstract = {The MxR Lab at the University of Southern California explores techniques and technologies to improve the fluency of humancomputer interactions and create engaging and effective synthetic experiences. With a research facility at the Institute for Creative Technologies as well as the satellite MxR Studio at the School of Cinematic Arts, this unique environment facilitates crossdisciplinary teams from computer science, engineering, communications, and cinema. The MxR Lab philosophy begins with rapid prototyping and playful exploration that progressively evolves to more refined development pipelines, formal research studies, and eventual dissemination through academic papers and open-source initiatives. We also sometimes engage in large-scale Nerf battles.},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
Jones, Andrew; Unger, Jonas; Nagano, Koki; Busch, Jay; Yu, Xueming; Peng, Hsuan-Yueh; Alexander, Oleg; Debevec, Paul
Building a Life-Size Automultiscopic Display Using Consumer Hardware Proceedings Article
In: Proceedings of GPU Technology Conference, San Jose, CA, 2015.
@inproceedings{jones_building_2015,
title = {Building a Life-Size Automultiscopic Display Using Consumer Hardware},
author = {Andrew Jones and Jonas Unger and Koki Nagano and Jay Busch and Xueming Yu and Hsuan-Yueh Peng and Oleg Alexander and Paul Debevec},
url = {http://ict.usc.edu/pubs/Building%20a%20Life-Size%20Automultiscopic%20Display%20Using%20Consumer%20Hardware.pdf},
year = {2015},
date = {2015-03-01},
booktitle = {Proceedings of GPU Technology Conference},
address = {San Jose, CA},
abstract = {Automultiscopic displays allow multiple users to experience 3D content without the hassle of special glasses or head gear. Such displays generate many simultaneous images with high-angular density, so that each eye perceives a distinct and different view. This presents a unique challenge for content acquisition and rendering. In this talk, we explain how to build an automultiscopic display using off-the-shelf projectors, video-splitters, and graphics cards. We also present a GPU-based algorithm for rendering a large numbers of views from a sparse array of video cameras.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Highland, Krista B.; Costanzo, Michelle E.; Jovanovic, Tanja; Norrholm, Seth D.; Ndiongue, Rochelle B.; Reinhardt, Brian J.; Rothbaum, Barbara; Rizzo, Albert A.; Roy, Michael J.
Catecholamine responses to virtual combat: implications for post-traumatic stress and dimensions of functioning Journal Article
In: Frontiers in Psychology, vol. 6, 2015, ISSN: 1664-1078.
@article{highland_catecholamine_2015,
title = {Catecholamine responses to virtual combat: implications for post-traumatic stress and dimensions of functioning},
author = {Krista B. Highland and Michelle E. Costanzo and Tanja Jovanovic and Seth D. Norrholm and Rochelle B. Ndiongue and Brian J. Reinhardt and Barbara Rothbaum and Albert A. Rizzo and Michael J. Roy},
url = {http://ict.usc.edu/pubs/Catecholamine%20responses%20to%20virtual%20combat%20-%20implications%20for%20post-traumatic%20stress%20and%20dimensions%20of%20functioning.pdf},
doi = {10.3389/fpsyg.2015.00256},
issn = {1664-1078},
year = {2015},
date = {2015-03-01},
journal = {Frontiers in Psychology},
volume = {6},
abstract = {Posttraumatic stress disorder (PTSD) symptoms can result in functional impairment among service members (SMs), even in those without a clinical diagnosis. The variability in outcomes may be related to underlying catecholamine mechanisms. Individuals with PTSD tend to have elevated basal catecholamine levels, though less is known regarding catecholamine responses to trauma-related stimuli. We assessed whether catecholamine responses to a virtual combat environment impact the relationship between PTSD symptom clusters and elements of functioning. Eighty-seven clinically healthy SMs, within 2 months after deployment to Iraq or Afghanistan, completed self-report measures, viewed virtual-reality (VR) combat sequences, and had sequential blood draws. Norepinephrine responses to VR combat exposure moderated the relationship between avoidance symptoms and scales of functioning including physical functioning, physical-role functioning, and vitality. Among those with high levels of avoidance, norepinephrine change was inversely associated with functional status, whereas a positive correlation was observed for those with low levels of avoidance. Our findings represent a novel use of a virtual environment to display combat-related stimuli to returning SMs to elucidate mind-body connections inherent in their responses. The insight gained improves our understanding of post-deployment symptoms and quality of life in SMs and may facilitate enhancements in treatment. Further research is needed to validate these findings in other populations and to define the implications for treatment effectiveness.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Maslan, Nicole; Roemmele, Melissa; Gordon, Andrew S.
One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology Proceedings Article
In: Proceedings of the Twelfth International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense-2015), Stanford, CA, 2015.
@inproceedings{maslan_one_2015,
title = {One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology},
author = {Nicole Maslan and Melissa Roemmele and Andrew S. Gordon},
url = {http://ict.usc.edu/pubs/One%20Hundred%20Challenge%20Problems%20for%20Logical%20Formalizations%20of%20Commonsense%20Psychology.PDF},
year = {2015},
date = {2015-03-01},
booktitle = {Proceedings of the Twelfth International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense-2015)},
address = {Stanford, CA},
abstract = {We present a new set of challenge problems for the logical formalization of commonsense knowledge, called Triangle-COPA. This set of one hundred problems is smaller than other recent commonsense reasoning question sets, but is unique in that it is specifically designed to support the development of logic-based commonsense theories, via two means. First, questions and potential answers are encoded in logical form using a fixed vocabulary of predicates, eliminating the need for sophisticated natural language processing pipelines. Second, the domain of the questions is tightly constrained so as to focus formalization efforts on one area of inference, namely the commonsense reasoning that people do about human psychology. We describe the authoring methodology used to create this problem set, and our analysis of the scope of requisite common sense knowledge. We then show an example of how problems can be solved using an implementation of weighted abduction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ward, Nigel G.; DeVault, David
Ten Challenges in Highly-Interactive Dialog Systems Proceedings Article
In: Proceedings of AAAI 2015 Spring Symposium, Palo Alto, CA, 2015.
@inproceedings{ward_ten_2015,
title = {Ten Challenges in Highly-Interactive Dialog Systems},
author = {Nigel G. Ward and David DeVault},
url = {http://ict.usc.edu/pubs/Ten%20Challenges%20in%20Highly-Interactive%20Dialog%20Systems.pdf},
year = {2015},
date = {2015-03-01},
booktitle = {Proceedings of AAAI 2015 Spring Symposium},
address = {Palo Alto, CA},
abstract = {Systems capable of highly-interactive dialog have recently been developed in several domains. This paper considers how to build on these successes to make systems more robust, easier to develop, more adaptable, and more scientifically significant.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Grechkin, Timofey; Azmandian, Mahdi; Bolas, Mark; Suma, Evan
Towards Context-Sensitive Reorientation for Real Walking in Virtual Reality Proceedings Article
In: 2015 IEEE Virtual Reality (VR), pp. 185–186, IEEE, Arles, France, 2015, ISBN: 978-1-4799-1727-3.
@inproceedings{grechkin_towards_2015,
title = {Towards Context-Sensitive Reorientation for Real Walking in Virtual Reality},
author = {Timofey Grechkin and Mahdi Azmandian and Mark Bolas and Evan Suma},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7223357},
doi = {10.1109/VR.2015.7223357},
isbn = {978-1-4799-1727-3},
year = {2015},
date = {2015-03-01},
booktitle = {2015 IEEE Virtual Reality (VR)},
pages = {185–186},
publisher = {IEEE},
address = {Arles, France},
abstract = {Redirected walking techniques have been introduced to overcome physical limitations for natural locomotion in virtual reality. Although subtle perceptual manipulations are helpful to keep users within relatively small tracked spaces, it is inevitable that users will approach critical boundary limits. Current solutions to this problem involve breaks in presence by introducing distractors, or freezing the virtual world relative to the user’s perspective. We propose an approach that integrates into the virtual world narrative to draw users’ attention and to cause them to temporarily alter their course to avoid going off bounds. This method ties together unnoticeable translation, rotation, and curvature gains, efficiently reorienting the user while maintaining the user’s sense of immersion. We also discuss how this new method can be effectively used in conjunction with other reorientation techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
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}
}
0000
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}
}
Bosnak, Robert E.; Bosnak, David E.; Rizzo, Albert
Systems and methods for ai driven generation of content attuned to a user Patent
US20240005583A1, 0000.
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},
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}
}
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}
}