Filters








2,971 Hits in 4.5 sec

Extended Hierarchical Task Network Planning for Interactive Comedy [chapter]

Ruck Thawonmas, Keisuke Tanaka, Hiroki Hassaku
2003 Lecture Notes in Computer Science  
To be able to maintain the story, we adopt hierarchical task network planning (HTN) for planning of a character agent.  ...  We then extend HTN such that the extended HTN allows for the direct use of character failures, higher interactions with the viewer, and more story variations.  ...  work has been supported in part by the Ritsumeikan University's Kyoto Art and Entertainment Innovation Research, a project of the 21 st Century Center of Excellence Program funded by the Japan Society for  ... 
doi:10.1007/978-3-540-39896-7_18 fatcat:drrfgixppbcevopsku5z66s4um

Planning characters' behaviour in interactive storytelling

Marc Cavazza, Fred Charles, Steven J. Mead
2002 Journal of Visualization and Computer Animation  
The set of possible roles for a given actor is represented as a Hierarchical Task Network (HTN).  ...  In this paper, we describe a method for implementing the behaviour of artificial actors in the context of interactive storytelling.  ...  Acknowledgements We are indebted to Eric Jacopin for his advice on AI planning formalisms: any remaining misconceptions are the authors' sole responsibility.  ... 
doi:10.1002/vis.285 fatcat:fzecvdi7afefhdkljzmjuv7gku

Beep! Beep! Boom!

David Olsen, Michael Mateas
2009 Proceedings of the 4th International Conference on Foundations of Digital Games - FDG '09  
Using a hierarchal task network (HTN) planner, the game plans out a gag based on the item attributes as well as the state of the world.  ...  Player's are able to interact with ACME by adding and removing objects from the world.  ...  We then use these insights to build up a hierarchical task network (HTN) planning domain that can represent the CRRC world and generate action sequences within it that follow its internal rule structure  ... 
doi:10.1145/1536513.1536544 dblp:conf/fdg/OlsenM09 fatcat:k53iezawwrhu5pmqjdxv35fyee

Origraph: Interactive Network Wrangling [article]

Alex Bigelow, Carolina Nobre, Miriah Meyer, Alexander Lex
2019 arXiv   pre-print
Data wrangling is widely acknowledged to be a critical part of the data analysis pipeline, yet interactive network wrangling has received little attention in the visualization research community.  ...  In addition, we introduce interfaces designed to aid analysts in specifying arguments for sensible network wrangling operations.  ...  For example, we could create a supernode that represents all comedy movies ( Figure 6 ).  ... 
arXiv:1812.06337v3 fatcat:wnibjvo2ujeatbs6pp46kmby24

How Top Talent Uses Networks and Where Rising Stars Get Trapped

ROB CROSS, ROBERT J. THOMAS
2008 Organizational Dynamics  
Others, meanwhile, peruse one self-help book after another in search for the quick-fix "secrets" to a power network.  ...  These frustrating experiences can lead people to take extreme attitudes toward networking, however. Some dismiss it as a game for selfpromoters and opt out of the activity altogether.  ...  Relationships that extend individual expertise In addition to being positioned well within an overall network, we found that top performers cultivate personal networks that extend their abilities and help  ... 
doi:10.1016/j.orgdyn.2008.02.001 fatcat:rslvto7amnajtf3egxpvitaqsu

VISAGE

Robert Pienta, Acar Tamersoy, Alex Endert, Shamkant Navathe, Hanghang Tong, Duen Horng Chau
2016 Proceedings of the International Working Conference on Advanced Visual Interfaces - AVI '16  
Extracting useful patterns from large network datasets has become a fundamental challenge in many domains.  ...  use and the ability to construct graph queries significantly faster than using a conventional query language; (4) VISAGE works on real graphs with over 468K edges, achieving sub-second response times for  ...  The feature-tree allows users to explore hierarchical and non-hierarchical features (for both categorical and continuous variables).  ... 
doi:10.1145/2909132.2909246 pmid:28553670 pmcid:PMC5444304 dblp:conf/avi/PientaTENTC16 fatcat:4fqcul3wafgjzad4426fujeiwi

Cue Me In: Content-Inducing Approaches to Interactive Story Generation [article]

Faeze Brahman, Alexandru Petrusca, Snigdha Chaturvedi
2020 arXiv   pre-print
Here, we instead focus on the task of interactive story generation, where the user provides the model mid-level sentence abstractions in the form of cue phrases during the generation process.  ...  This provides an interface for human users to guide the story generation. We present two content-inducing approaches to effectively incorporate this additional information.  ...  In the rest of this section, we describe our two novel content-inducing approaches for addressing the interactive story generation task: the Cued Writer, and the Relevance Cued Writer.  ... 
arXiv:2010.09935v1 fatcat:uukfnbtdkvdxhnmt442vmizbb4

SceneMaker: Intelligent Multimodal Visualisation of Natural Language Scripts [chapter]

Eva Hanser, Paul Mc Kevitt, Tom Lunney, Joan Condell
2010 Lecture Notes in Computer Science  
are presented along with a development plan and test scenarios.  ...  For this purpose a web based software prototype, SceneMaker, will be developed.  ...  SmartKom supports tasks of 50 different domains for scenarios in the car or for pedestrians with an extendable unified knowledge base.  ... 
doi:10.1007/978-3-642-17080-5_17 fatcat:w23elmcseja3lfycqehk5awdju

Analysis of Computer-Mediated Communication: Using Formal Concept Analysis as a Visualizing Methodology

Noriko Hara
2002 Journal of educational computing research  
The purpose of this article is to provide an example of the application of FCA to CMC and to argue for its potential use for analyzing on-line discourse.  ...  Although this article specifically addresses issues related to analyzing data in CMC for education, the methodology is applicable to the analysis of CMC for different purposes.  ...  Computers have extended human intellectual processes (Harasim, 1990) . Mason and Kaye (1990) promote the potential use of CMC for distance education.  ... 
doi:10.2190/9w69-ul5k-dvnj-bmt3 fatcat:c37khce2gvcbxonfondwnk3ev4

Graph-based Topic Extraction from Vector Embeddings of Text Documents: Application to a Corpus of News Articles [article]

M. Tarik Altuncu, Sophia N. Yaliraki, Mauricio Barahona
2020 arXiv   pre-print
Hence pre-trained BERT models without fine-tuning are not optimised for the quality of their vector embedding, which is the primary input for our unsupervised clustering task.  ...  Natural Language Inference (NLI) tasks.  ... 
arXiv:2010.15067v1 fatcat:jzn6kphngzebvkexccrubnxnfi

"Suggest me a movie for tonight": Leveraging Knowledge Graphs for Conversational Recommendation

Rajdeep Sarkar, Koustava Goswami, Mihael Arcan, John P. McCrae
2020 Zenodo  
Conversational recommender systems focus on the task of suggesting products to users based on the conversation flow.  ...  In this work, we study several subgraph construction methods and compare their performance across the recommendation task.  ...  We would also like to thank the anonymous reviewers for their insights on this work.  ... 
doi:10.5281/zenodo.4320720 fatcat:ithjjhf2yzbxngav3tg7cqzsdi

Internet Categorization and Search: A Self-Organizing Approach

Hsinchun Chen, Chris Schuffels, Richard Orwig
1996 Journal of Visual Communication and Image Representation  
We consider sults of our recent testing of a multilayered neural network that devising a scalable approach to Internet search is criticlustering algorithm employing the Kohonen self-organizing cal to the  ...  research aims to provide an sources, their use is accompanied by the problem of users alternative concept-based categorization and search capability not being able to explore and find what they want in an for  ...  a multilayered neural network clustering algorithm employing a Kohonen self-organizing have used different neural networks for more specific tasks.  ... 
doi:10.1006/jvci.1996.0008 fatcat:dlisw7bpercglkq6w3llzabdii

LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations [article]

Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis, Kai Fricke, Felix Gessert, Eiko Yoneki
2018 arXiv   pre-print
In this work, we introduce LIFT, an end-to-end software stack for applying deep reinforcement learning to data management tasks.  ...  Recent successes in combining deep neural networks with reinforcement learning have sparked significant new interest in this domain.  ...  We initially focus on common query operators available in most query dialects, as we plan to extend our work to other database layouts and query languages. Table 1 gives an operator overview.  ... 
arXiv:1808.07903v1 fatcat:wdzhvtufmnggthgzjxcllqxriy

Recognizing Induced Emotions of Movie Audiences From Multimodal Information

Michal Muszynski, Leimin Tian, Catherine Lai, Johanna Moore, Theodoros Kostoulas, Patrizia Lombardo, Thierry Pun, Guillaume Chanel
2019 IEEE Transactions on Affective Computing  
To carry out analysis of induced and perceived emotions, we first extended an existing database for movie affect analysis by annotating perceived emotions in a crowd-sourced manner.  ...  Recognizing emotional reactions of movie audiences to affective movie content is a challenging task in affective computing.  ...  In addition, other researchers proposed to use Deep Belief Networks (DBNs) to capture complex non-linear interactions in audio-visual features for emotion recognition [12] .  ... 
doi:10.1109/taffc.2019.2902091 fatcat:c2fr4td7u5dqlk4ya4njwdviau

On the generation of rich content metadata from social media

Giacomo Inches, Andrea Basso, Fabio Crestani
2011 Proceedings of the 3rd international workshop on Search and mining user-generated contents - SMUC '11  
This contribution proposes a framework to generate auxiliary rich TV content metadata by processing Social Networks data.  ...  This is a first step towards integrating relevant social media information to enhance the description of TV content as well as for generating recommendations based on social data.  ...  In future studies we want to investigate better these preliminary considerations in particular those aspect of "social" interaction, also extending the set of streams to a significative sample of generic  ... 
doi:10.1145/2065023.2065042 dblp:conf/cikm/InchesBC11 fatcat:uy7arh5kfrhrtpoxy7rychazjm
« Previous Showing results 1 — 15 out of 2,971 results