Filters








599,182 Hits in 14.2 sec

Out of context: Computer systems that adapt to, and learn from, context

H. Lieberman, T. Selker
2000 IBM Systems Journal  
Smart computers,intelligent agentsoftware,and digital devicesof the futurewillhaveto operateon data thatare not explicitlygivento them,data that theyobserveor gatherfor themselves.  ...  In otherwords,context.But what, exactly,is context?  ...  We rely on our human agents to learn from past experience and to be able to pick up information they need from context.  ... 
doi:10.1147/sj.393.0617 fatcat:3roilp7exvbk3d3nteukkdyu3u

Taking it out of context

Leslie D. Setlock, Susan R. Fussell, Christine Neuwirth
2004 Proceedings of the 2004 ACM conference on Computer supported cooperative work - CSCW '04  
In this study, 24 pairs in three cultural groupings-American-American (AA), Chinese-Chinese (CC) and American-Chinese (AC) -worked on two decision-making tasks, one face-to-face and the other via IM.  ...  The quantitative results combined with conversation analysis suggest that the groups viewed the task differently-AA pairs as an exercise in situation-specific compromise; CC as consensus-reaching.  ...  We thank Adam Kramer for adapting his TAWC software for our project and for running analyses, and Mariesa Cash, Monica Datta, Sarah Shipul and Jim Zheng for their assistance in running experiments and  ... 
doi:10.1145/1031607.1031712 dblp:conf/cscw/SetlockFN04 fatcat:3g3dm4tzpfcqndsuvgcdsie37y

Out of Context - Understanding the Practicalities of Learning Games

Björn Marklund
2014 Conference of the Digital Games Research Association  
the of Game .  ...  My gratitude goes out to Per Backlund, Henrik Engström, and Anna-Sofia Alklind Taylor for their invaluable input.  ...  Learning games need to break into a context that is not currently built to support them, and in that context perform better than means that teachers and students are previously familiar with and adept  ... 
dblp:conf/digra/Marklund14 fatcat:44gqk34szrdjjj6l2dejz4pf5q

Mix3D: Out-of-Context Data Augmentation for 3D Scenes [article]

Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann
2021 arXiv   pre-print
By doing so, object instances are implicitly placed into novel out-of-context environments and therefore making it harder for models to rely on scene context alone, and instead infer semantics from local  ...  We perform detailed analysis to understand the importance of global context, local structures and the effect of mixing scenes.  ...  Acknowledgments: This work is supported by the ERC Consolidator Grant DeeViSe (ERC-2017-CoG-773161) and compute resources from RWTH Aachen University (rwth0629, thes0775).  ... 
arXiv:2110.02210v2 fatcat:u4dro3eclnhu3mkmbahrp2f3am

Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis [article]

Bowen Xing, Ivor W. Tsang
2022 arXiv   pre-print
To address this problem, we argue the given aspect should be considered as a new clue out of context in the context modeling process.  ...  The core of ABSA is to model the interaction between the context and given aspect to extract the aspect-related information.  ...  Acknowledgements This work was supported by Australian Research Council Grant (DP180100106 and DP200101328).  ... 
arXiv:2106.10816v2 fatcat:xkwguhqxxfgbzasn7kxoiifn6q

Identifying and Benchmarking Natural Out-of-Context Prediction Problems [article]

David Madras, Richard Zemel
2021 arXiv   pre-print
Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of making reliable predictions on uncommon or unusual inputs or subgroups of the training distribution.  ...  We present NOOCh: a suite of naturally-occurring "challenge sets", and show how varying notions of context can be used to probe specific OOC failure modes.  ...  Acknowledgments and Disclosure of Funding Thanks to Marc-Etienne Brunet, Eleni Triantafilliou and Elliot Creager for their helpful thoughts on the manuscript, as well as to four anonymous reviewers for  ... 
arXiv:2110.13223v1 fatcat:3ahhrmxzmfhjhgi6qtdz47ap6i

Mix3D: Out-of-Context Data Augmentation for 3D Scenes

Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann
2021 2021 International Conference on 3D Vision (3DV)  
By doing so, object instances are implicitly placed into novel out-of-context environments, therefore making it harder for models to rely on scene context alone, and instead infer semantics from local  ...  We perform detailed analysis to understand the importance of global context, local structures and the effect of mixing scenes.  ...  Acknowledgments: This work is supported by the ERC Consolidator Grant DeeViSe (ERC-2017-CoG-773161) and compute resources from RWTH Aachen University (rwth0629, thes0775).  ... 
doi:10.1109/3dv53792.2021.00022 fatcat:pyn75hl5ffdpnivnux67y6fari

Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis

Bowen Xing, Ivor W. Tsang
2022 The Journal of Artificial Intelligence Research  
To address this problem, we argue the given aspect should be considered as a new clue out of context in the context modeling process.  ...  The core of ABSA is to model the interaction between the context and given aspect to extract aspect-related information.  ...  Acknowledgements This work was supported by Australian Research Council Grant (DP180100106 and DP200101328).  ... 
doi:10.1613/jair.1.13410 fatcat:gus27fk7mbb6fekik67cn6qoaa

Taking Attention Out of Context: Frontopolar Transcranial Magnetic Stimulation Abolishes the Formation of New Context Memories in Visual Search

Artyom Zinchenko, Markus Conci, Paul C. J. Taylor, Hermann J. Müller, Thomas Geyer
2019 Journal of Cognitive Neuroscience  
) to see how FPC rTMS influences the ability of observers to adapt context-based memories acquired in the training phase.  ...  This finding shows that FPC plays an important role in the regulation of prediction errors in statistical context learning, thus contributing to an update of the spatial target-distractor contingencies  ...  Acknowledgments This research was supported by a project grant from the German research foundation (Deutsche Forschungsgemeinschaft, DFG, grant GE 1889/4-1 to T. G. and M. C. and TA 857/3-1 to P.  ... 
doi:10.1162/jocn_a_01358 pmid:30457915 fatcat:gc6lavxo2jghbgwqmxj2cuniue

How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction [article]

Anthony Bau, Jacob Andreas
2021 arXiv   pre-print
We show that RNN and transformer language models exhibit structured, consistent generalization in out-of-distribution contexts.  ...  These results help explain the effectiveness of two popular regularization schemes and show that aspects of sequence model generalization can be understood and controlled.  ...  In the global context model, it is the most recent word, and not the rest of the context, that as treated as a possible source of noise to be marginalized out rather than conditioned on.  ... 
arXiv:2111.03108v1 fatcat:jaef4g4tbve57lf5ijsu5k6qhy

Out of Context: NMDA Receptor Antagonism in the Avian 'Prefrontal Cortex' Impairs Context Processing in a Conditional Discrimination Task

Silke Lissek, Onur Güntürkün
2005 Behavioral Neuroscience  
N-methyl-D-aspartate (NMDA) receptors in the mammalian prefrontal cortex (PFC) and in the nidopallium caudolaterale (NCL) of birds, the avian functional equivalent of the PFC, are involved in learning,  ...  which also requires processing of context.  ...  The Skinner box was equipped with three pecking keys and a solenoid-operated food hopper and was computer controlled by means of a digital input-output board controlled by the special Operant Learning  ... 
doi:10.1037/0735-7044.119.3.797 pmid:15998201 fatcat:hadkzhzpkrdkpcsh6eibkjnzqa

Taken Out of Context: American Teen Sociality in Networked Publics

danah boyd
2008 Social Science Research Network  
Teens leveraged these sites for a wide array of everyday social practices-gossiping, flirting, joking around, sharing information, and simply hanging out.  ...  As social network sites like MySpace and Facebook emerged, American teenagers began adopting them as spaces to mark identity and socialize with peers.  ...  Melanie, a white 15-year-old in Kansas, points out that the "computer mask" is extremely valuable for learning how to negotiate relationships, especially in middle school.  ... 
doi:10.2139/ssrn.1344756 fatcat:yijalpqxtrc7rhzzyaj2opqp5u

Contextual cueing of pop-out visual search: When context guides the deployment of attention

T. Geyer, M. Zehetleitner, H. J. Muller
2010 Journal of Vision  
Thus, contextual cueing can expedite the selection of pop-out targets, most likely by enhancing feature contrast signals at the overall-salience computation stage.  ...  Visual context information can guide attention in demanding (i.e., inefficient) search tasks.  ...  cueing effect to be more pronounced in the fixed than in the variable dimension-context-mapping condition (e.g., presenting color and orientation targets within the same contexts could have made learning  ... 
doi:10.1167/10.5.20 pmid:20616131 fatcat:4wskoqpbuncwlmahypou5g6cua

Shelf based out-of-stocks in the context of employee density

Aleksandar Grubor, Nikola Milicevic, Nenad Djokic, Nemanja Berber
2017 Engineering Economics  
The results showed that the relation between employee density and shelf based out-of-sock varied among different formats.  ...  The purpose of this paper is to investigate the effect of employee density on shelf based out-of-stocks, i.e. situations when products are physically present at stores, but not on the marked sale positions  ...  The required number of employees can also be set by the use of computerized scheduling systems, whereby size of the staff is adapted to the estimated total workload (Ton, 2008) .  ... 
doi:10.5755/j01.ee.28.4.16194 fatcat:2czx2fjtqbgjrlew5c6watmnia

Standing out in a networked communication context: Toward a network contingency model of public attention

Aimei Yang, Adam J Saffer
2020 New Media & Society  
This study takes a strategic network perspective and draws from recent research in network science to propose the network contingency model of public attention.  ...  To test the model, we combine data mining, social network analysis, and machine-learning techniques to analyze a large-scale Twitter discussion network.  ...  Building from this approach, Sommerfeldt and Yang (2017) explained that social movement organizations need to adapt their network-building strategies to their goals.  ... 
doi:10.1177/1461444820939445 fatcat:ezlotos7gfdtbknwn6k7vuknhq
« Previous Showing results 1 — 15 out of 599,182 results