Filters








12,148 Hits in 6.9 sec

By their apps you shall understand them

Trinh-Minh-Tri Do, Daniel Gatica-Perez
2010 Proceedings of the 9th International Conference on Mobile and Ubiquitous Multimedia - MUM '10  
fit their needs.  ...  Our methodology involves the design of a bag-of-apps model that robustly represents level of phone usage over specific times of the day, and the use of a probabilistic topic model that jointly discovers  ...  Topic models assume that observations are a mixture of topics. In other words, one day may be generated from various topics and a user may have different behaviors.  ... 
doi:10.1145/1899475.1899502 dblp:conf/mum/DoG10 fatcat:tugx7ynvfzfmpjtebw5pdyr75q

What Do You Do When You Know That You Don't Know?

Abhijit Bendale, Terrance E. Boult
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We also develop a general approach to estimating SVM refactoring risk. We present experiments on large-scale face recognition based on describable visual attributes on LFW dataset.  ...  We introduce the concept of "operational adaptation" for biometric systems and formalize the problem.  ...  In this particular definition, while we presume that M is given, a more general form may involve estimating M .  ... 
doi:10.1109/cvprw.2016.16 dblp:conf/cvpr/BendaleB16a fatcat:exmzvvc7frgvdbvl6am7xuuhbi

Finding your friends and following them to where you are

Adam Sadilek, Henry Kautz, Jeffrey P. Bigham
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
For location prediction, Flap implements a scalable probabilistic model of human mobility, where we treat users with known GPS positions as noisy sensors of the location of their friends.  ...  For link prediction, Flap infers social ties by considering patterns in friendship formation, the content of people's messages, and user location.  ...  They model the relationship as an exponential probability distribution and show it fits well to the observed, empirical distribution.  ... 
doi:10.1145/2124295.2124380 dblp:conf/wsdm/SadilekKB12 fatcat:ha6goxl3bvanjbsc7qvfzwwfeu

5. Damned If You Do, Damned If You Don't [chapter]

1993 Lifting a Ton of Feathers  
Additionally aid from neighbouring countries potentially promotes improvement of infrastructure on a regional level, which may benefit not only the recipient but also the donor as a user of the infrastructure  ...  (Johnson 2003) A number of cross-drainage works were planned to siphon off water where the canal crossed, crossing points were planned for humans and animals, and ferry boats and cattle ramps would be  ... 
doi:10.3138/9781442659858-009 fatcat:koedfhdcdngadcx4pnaci4svj4

Bootstrap Latent Representations for Multi-modal Recommendation [article]

Xin Zhou, Hongyu Zhou, Yong Liu, Zhiwei Zeng, Chunyan Miao, Pengwei Wang, Yuan You, Feijun Jiang
2022 arXiv   pre-print
It then jointly optimizes three multi-modal objectives to learn the representations of users and items by reconstructing the user-item interaction graph and aligning modality features under both inter-  ...  which increases the computational cost on large graphs and may also bring noisy supervision signals into the training process.  ...  The authors would like to express thanks to Professor Aixin Sun from Nanyang Technological University for his valuable suggestions.  ... 
arXiv:2207.05969v1 fatcat:kzsbdqc2oncvrlvuz22o64wecq

Words are all you need? Capturing human sensory similarity with textual descriptors [article]

Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
2022 arXiv   pre-print
We further show that the degree to which textual descriptors and models predict human similarity varies across and within modalities.  ...  We present an interactive visualization at https://words-are-all-you-need.s3.amazonaws.com/index.html for exploring the similarity between stimuli as experienced by humans and different methods reported  ...  Acknowledgments and Disclosure of Funding This work was supported by a grant from the John Templeton Foundation to TLG and an NDSEG Fellowship to TRS.  ... 
arXiv:2206.04105v2 fatcat:occ2ypk4rfhsjow6puz66mw7f4

Attend to You: Personalized Image Captioning with Context Sequence Memory Networks [article]

Cesc Chunseong Park, Byeongchang Kim, Gunhee Kim
2017 arXiv   pre-print
over state-of-the-art captioning models.  ...  users.  ...  Gunhee Kim is the corresponding author.  ... 
arXiv:1704.06485v2 fatcat:pkoxr7glhfdyzlx4vhnlzypc6i

Tell Me Something That Will Help Me Trust You: A Survey of Trust Calibration in Human-Agent Interaction [article]

George J. Cancro, Shimei Pan, James Foulds
2022 arXiv   pre-print
When a human receives a prediction or recommended course of action from an intelligent agent, what additional information, beyond the prediction or recommendation itself, does the human require from the  ...  agent to decide whether to trust or reject the prediction or recommendation?  ...  This construct allows for flexibility in low-cost and high-cost operations as well as providing for cross over cases when a low-cost user wants to understand more or when a high-cost user wants communications  ... 
arXiv:2205.02987v1 fatcat:6imqgkctprayrnpift2ybwc7u4

Cross-modality Consistent Regression for Joint Visual-Textual Sentiment Analysis of Social Multimedia

Quanzeng You, Jiebo Luo, Hailin Jin, Jianchao Yang
2016 Proceedings of the Ninth ACM International Conference on Web Search and Data Mining - WSDM '16  
Motivated by the needs to leverage large-scale social multimedia content for sentiment analysis, we propose a cross-modality consistent regression (CCR) model, which is able to utilize both the state-of-the-art  ...  Sentiment analysis of online user generated content is important for many social media analytics tasks.  ...  Acknowledgements This work was generously supported in part by Adobe Research, and New York State CoE IDS. Jianchao Yang performed related work while he was with Adobe Research.  ... 
doi:10.1145/2835776.2835779 dblp:conf/wsdm/YouLJY16 fatcat:sdiu7gg45naj7ewgwrxkxaspia

What you see is what you get? - A comparison of theoretical lenses to study technology in organizations

Benjamin Müller, Philip Raeth
2012 International Conference on Information Systems  
In doing so, the paper identifies and analyzes five emergent issues in theorizing across the three lenses: the role and nature of technology, technological change, changing practice, organizational change  ...  The paper thus presents other researchers with an opportunity to reflect upon the authors' experiences and supports the choice of an appropriate theoretical lens for studying technology in organizations  ...  ), and later periods (management, general wiki users, other departments) of the Hermes Wiki.  ... 
dblp:conf/icis/MuellerR12 fatcat:4jh7vbu72jeeld5hs5d2owcsam

Can You Play with Fire and Not Hurt Yourself? A Comparative Study in Figurative Language Comprehension between Individuals with and without Autism Spectrum Disorder

Sobh Chahboun, Valentin Vulchanov, David Saldaña, Hendrik Eshuis, Mila Vulchanova, Philip Allen
2016 PLoS ONE  
We were interested in the extent to which visual context, e.g., an image corresponding either to the literal meaning or the figurative meaning of the expression may facilitate responses to such expressions  ...  Participants with HFA and their typically developing peers (matched on intelligence and language level) completed a cross-modal sentencepicture matching task for figurative expressions and their target  ...  Acknowledgments We would like to thank the participants and the families for their effort and time in participating in this study.  ... 
doi:10.1371/journal.pone.0168571 pmid:28036344 pmcid:PMC5201294 fatcat:hu4vsgirvfdc5hlf6h2b57f32m

You are what you eat: market citizens and the right to know about nano foods

Elen Stokes
2011 Journal of Human Rights and the Environment  
The potential benefits of nano labelling are substantial. As this article seeks to show, however, the demands placed on nano labelling may be difficult to meet because of a range of limiting factors.  ...  This article considers the role of consumers in the regulation of nanotechnology. The principal regulatory response to nanotechnology to date has been to require the disclosure of information.  ...  is the face that the public is seeing.  ... 
doi:10.4337/jhre.2011.02.03 fatcat:mvo2e4mtrjcwtf4npqs4e47z5m

It ain't what you do, it's the way that you do it – that's what gets results

S Munslow, MG Wallis
2002 Breast Cancer Research  
two modalities.  ...  MRI is the most reliable modality for identifying and characterising rupture (sensitivity 95%, specificity 93% Women who attend for breast screening are in general not motivated by ill health.  ... 
doi:10.1186/bcr502 fatcat:7qrjojjkmfclpg2z57lv6phwly

Fast character modeling with sketch-based PDE surfaces

Lihua You, Xiaosong Yang, Junjun Pan, Tong-Yee Lee, Shaojun Bian, Kun Qian, Zulfiqar Habib, Allah Bux Sargano, Ismail Kazmi, Jian J. Zhang
2020 Multimedia tools and applications  
Most research activities investigate how to retrieve a 3D template model to match 2D sketches [10] and deform a 3D template model to fit the silhouette in one single view [21, 22] .  ...  The sketch-guided global modeling generates a character model from three different levels of sketched profile curves called primary, secondary and key cross-section curves in three orthographic views.  ...  The final detailed model is obtained by fitting user-drawn key cross-section profile curves which deforms the intermediate model to change the elliptic crosssection curves into the user-drawn real key  ... 
doi:10.1007/s11042-020-09060-9 fatcat:pufozqs45venjjgkdpya5wgyci

Can You Hear Me Now? The Impact of Voice in an Online Gaming Community

Dmitri Williams, Scott Caplan, Li Xiong
2007 Human Communication Research  
The findings are discussed with respect to social capital, cyberbalkanization, and the general computer-mediated communication literature, with special attention paid to social information processing theory  ...  However, most researchers have dismissed the cues-filtered-out model in light of evidence indicating that CMC interactions are  ...  Introducing cues allows the presence of true boundary crossing as individuals learn the demographic backgrounds and personalities of the other players, yet those same characteristics may offer them reasons  ... 
doi:10.1111/j.1468-2958.2007.00306.x fatcat:g2fkxq5csvhc7gdcppomzmxkye
« Previous Showing results 1 — 15 out of 12,148 results