Filters








376 Hits in 3.4 sec

Learning Generalizable Visual Representations via Interactive Gameplay [article]

Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M Pratt, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, Ali Farhadi
2021 arXiv   pre-print
Here we are the first to show that embodied adversarial reinforcement learning agents playing Cache, a variant of hide-and-seek, in a high fidelity, interactive, environment, learn generalizable representations  ...  value of moving from large, static, datasets towards experiential, interactive, representation learning.  ...  Visual representation learning should move away from large, static, datasets and towards experiential, interactive, learning.  ... 
arXiv:1912.08195v3 fatcat:gocilpb4z5d7bjldotilzeztr4

The Pixels and Sounds of Emotion: General-Purpose Representations of Arousal in Games [article]

Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
2021 arXiv   pre-print
the video footage of their gameplay.  ...  Is it possible, for instance, to design general-purpose representations that detect affect solely from the pixels and audio of a human-computer interaction video?  ...  As gameplay videos are largely available online in massive quantities-e.g. via service such as Twitch 1 and Mixer 2 -the proposed approach is potentially generalizable to any game with available audiovisual  ... 
arXiv:2101.10706v3 fatcat:w3rc3oh2s5faviiea7w75heze4

Modeling Individual and Team Behavior through Spatio-temporal Analysis [article]

Sabbir Ahmad, Andy Bryant, Erica Kleinman, Zhaoqing Teng, Truong-Huy D. Nguyen, Magy Seif El-Nasr
2020 arXiv   pre-print
In this paper, we present a new methodology, called Interactive Behavior Analytics (IBA), comprised of two visualization systems, a labeling mechanism, and abstraction algorithms that use Dynamic Time  ...  machine learning models using visualization [38, 37] .  ...  The new version, shown in Figure 3 , is composed of three visual representations (as opposed to two in the original system): a state graph (right), a sequence graph (upper left) and a group graph (bottom  ... 
arXiv:2006.11199v1 fatcat:ztoldw4jmfgrtphnugkydkqjpu

Adapting Cognitive Task Analysis to Elicit the Skill Chain of a Game

Britton Horn, Seth Cooper, Sebastian Deterding
2017 Proceedings of the Annual Symposium on Computer-Human Interaction in Play - CHI PLAY '17  
While effective in foregrounding overlooked low-level skills required by a game, its efficiency and generalizability remain to be proven.  ...  For players to optimally learn and enjoy a game, it should introduce skill atoms in the ideal sequence of this hierarchy or chain.  ...  To elicit representational and decision-making skills via critical decisions and errors, the analyst watches the unfolding play and makes time-stamped notes on these incidents for focused follow-up.  ... 
doi:10.1145/3116595.3116640 dblp:conf/chiplay/HornCD17 fatcat:k567jlpr3rb5voe5k6pgvsrgpa

"And then they died": Using Action Sequences for Data Driven,Context Aware Gameplay Analysis [article]

Erica Kleinman, Sabbir Ahmad, Zhaoqing Teng, Andy Bryant, Truong-Huy D. Nguyen, Casper Harteveld, Magy Seif El-Nasr
2020 arXiv   pre-print
data analysis methodology that uses behavioral labels and visualizations to allow analysts to examine player behavior in a way that is context sensitive, scalable, and generalizable.  ...  Popular methodologies focus on machine learning and statistical analysis of aggregated data.  ...  Win prediction is another goal commonly pursued via quantitative techniques such as machine learning.  ... 
arXiv:2006.10823v1 fatcat:aidrizomnrberktgjqteylgv4e

Knowledge Encoding in Game Mechanics: Transfer-Oriented Knowledge Learning in Desktop-3D and VR

Sebastian Oberdörfer, Marc Erich Latoschik
2019 International Journal of Computer Games Technology  
Using immersive Virtual Reality (VR) has the potential to even further increase the serious game's learning outcome and learning quality.  ...  The study also indicates that VR is beneficial for the overall learning quality and that an enhanced audiovisual encoding has only a limited effect on the learning outcome.  ...  Also, we like to thank David Heidrich for his work in overhauling GEtiT, changing its visual style, and developing GEtiT VR.  ... 
doi:10.1155/2019/7626349 fatcat:wyxo3fqr45ex7lw4kn5mmu4llq

Extending neuro-evolutionary preference learning through player modeling

Hector P. Martinez, Kenneth Hullett, Georgios N. Yannakakis
2010 Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games  
Our approach extends neuro-evolutionary preference learning by embedding a player modeling module for the prediction of player preferences.  ...  of preference learning significantly and shows promise for the construction of more accurate cognitive and affective models. 978-1-4244-6297-1/10/$26.00 c 2010 IEEE  ...  Fig. 4 . 4 Visual representations of the best-performing ESOM: U-matrix, P-matrix and the three component (feature) planes.  ... 
doi:10.1109/itw.2010.5593340 dblp:conf/cig/MartinezHY10 fatcat:oamevkkr2rdbrnprkw2bkwtx24

CTArcade: Computational thinking with games in school age children

Tak Yeon Lee, Matthew Louis Mauriello, June Ahn, Benjamin B. Bederson
2014 International Journal of Child-Computer Interaction  
However, they expressed difficulty developing algorithmic representation of their gameplay strategy.  ...  In order to show generalizability of the CTArcade platform, we hope to develop more games with diverse interaction models.  ... 
doi:10.1016/j.ijcci.2014.06.003 fatcat:ejjxnetn7nafndzjllsyq7r72m

Towards general models of player affect

Elizabeth Camilleri, Georgios N. Yannakakis, Antonios Liapis
2017 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)  
We construct models mapping ranks of arousal to skin conductance and gameplay logs via preference learning and we use a form of cross-game validation to test the generality of the obtained models on unseen  ...  Models in this paper similarly learn the pairwise ranks of affect via preference learning.  ...  via computer vision applied on the video playthrough itself, via for instance deep preference learning [33] .  ... 
doi:10.1109/acii.2017.8273621 dblp:conf/acii/CamilleriYL17 fatcat:a36t346csnc3vong4otduxepae

Glyph: Visualization Tool for Understanding Problem Solving Strategies in Puzzle Games [article]

Truong-Huy Dinh Nguyen, Magy Seif El-Nasr, Alessandro Canossa
2021 arXiv   pre-print
for individual behavior, are not specifically designed to reduce the visual cognitive load.  ...  For academic researchers using games for serious purposes such as education, the strategies adopted by players are indicative of their cognitive progress in relation to serious goals, such as learning  ...  This work is funded by Northeastern University Tier 1 Grant: Learning Analytics.  ... 
arXiv:2106.13742v1 fatcat:tk7ygzqtendmredbo2tgpi5mfa

Glyph: Visualization Tool for Understanding Problem Solving Strategies in Puzzle Games

Truong-Huy D. Nguyen, Magy Seif El-Nasr, Alessandro Canossa
2015 International Conference on Foundations of Digital Games  
for individual behavior, are not specifically designed to reduce the visual cognitive load.  ...  For academic researchers using games for serious purposes such as education, the strategies adopted by players are indicative of their cognitive progress in relation to serious goals, such as learning  ...  This work is funded by Northeastern University Tier 1 Grant: Learning Analytics.  ... 
dblp:conf/fdg/NguyenEC15 fatcat:bisjyvjt7zg4hfqph4rixyjqru

Collecting Digital Biomarkers on Cognitive Health Through Computer Vision and Gameplay: an Image Processing Toolkit for Card Games

Karsten Gielis, Joren Kennes, Christophe De Dobbeleer, Steven Puttemans, Vero Vanden Abeele
2019 2019 IEEE International Conference on Healthcare Informatics (ICHI)  
Digital biomarkers obtained via gameplay have potential to aid in early diagnosing of cognitive health issues.  ...  By utilizing machine learning and image processing, gameplay can be analyzed in real-time and digital biomarkers can be extracted and processed in an efficient manner.  ... 
doi:10.1109/ichi.2019.8904511 dblp:conf/ichi/GielisKDPA19 fatcat:4x2t5m24irds3hgomrd3v5sntm

The Effect of Interactivity with a Music Video Game on Second Language Vocabulary Recall

Jonathan DeHaan, W. Michael Reed, Katsuko Kuwada
2010 Language Learning and Technology  
We relate these findings to theories and studies of vocabulary acquisition and video game-based language learning, and then suggest implications for language teaching and learning with interactive multimedia  ...  Video games are potential sources of second language input; however, the medium's fundamental characteristic, interactivity, has not been thoroughly examined in terms of its effect on learning outcomes  ...  ., stories, play, subtitles, repetition, feedback, and visual representations of language) should continue to be examined.  ... 
doaj:35e1082a0281418b9568ab7f7d8c95bf fatcat:xl2b2fwmdzcmdikbxfpdij3twu

Extracting Design Guidelines for Wearables and Movement in Tabletop Role-Playing Games via a Research Through Design Process

Oğuz Turan Buruk, Oğuzhan Özcan
2018 Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18  
We believe that wearables and movement are perfect fit for enhancing tabletop role-playing (TTRPG) experience, since they can provide embodied interaction, are perceived as character-costumes, enhance  ...  Interaction designers were to assist projects in terms of interaction techniques while the jewelry designers helped in the visual design.  ...  gameplay.  ... 
doi:10.1145/3173574.3174087 dblp:conf/chi/BurukO18 fatcat:jkjm4kp5jbf6hkeqdrjhml535e

Press A to Jump: Design Strategies for Video Game Learnability

Lev Poretski, Anthony Tang
2022 CHI Conference on Human Factors in Computing Systems  
We chose only the playthroughs that include only audio-visual stream of gameplay -with no external commentary from players and no interactions between the players and the audience of viewers 2 .  ...  In less complex games, games usually implement simpler variations, such as a single window, sheet, or screen with learning information breakdown accessible at any time via the in-game menu.  ... 
doi:10.1145/3491102.3517685 fatcat:fxshwjjzhzd3rdv7bdagkxtgti
« Previous Showing results 1 — 15 out of 376 results