A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Transfer learning to account for idiosyncrasy in face and body expressions
2013
2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
Preserved Fulltext
In this paper we investigate the use of the Transfer Learning (TL) framework to extract the commonalities across a set of subjects and also to learn the way each individual instantiates these commonalities ...
We compare our approaches with Ridge Regression which is a comparable model without the Transfer Learning property; as well as with a subtractive method for removing idiosyncrasy. ...
ACKNOWLEDGEMENTS The authors of this study are funded by the Engineering and Physical Sciences Research Council, UK (EP/H017178/1), Leicester: EP/H017194/1; part of the Pain rehabilitation: E/Motion-based ...
doi:10.1109/fg.2013.6553779
dblp:conf/fgr/Romera-ParedesAPBWW13
fatcat:taztyr4umfejnpxxx3ijc6mine
Reconstruction of Personalized 3D Face Rigs from Monocular Video
2016
ACM Transactions on Graphics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
We represent person specific idiosyncrasies, which can not be represented in the restricted shape and expression space, by learning a set of medium-scale corrective shapes. ...
We show captured face rigs and their motions for several actors filmed in different monocular video formats, including legacy footage from YouTube, and demonstrate how they can be used for 3D animation ...
ACKNOWLEDGMENTS We thank all the reviewers for their valuable comments and True-VisionSolutions Pty Ltd for kindly providing the 2D face tracker. ...
doi:10.1145/2890493
fatcat:4a7lvmi3ebcfhhldcknvj2blye
Cultural Communication Idiosyncrasies in Human-Computer Interaction
2016
Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this work, we investigate whether the cultural idiosyncrasies found in humanhuman interaction may be transferred to human-computer interaction. ...
We conducted a survey among Germans and Japanese to investigate whether the supposed differences may be applied in human-computer interaction. ...
This research and development work was also supported by the MIC/SCOPE #152307004. ...
doi:10.18653/v1/w16-3610
dblp:conf/sigdial/MiehleYPUNM16
fatcat:n7qguex3bzcsxcio65jncvozlu
Learning Speech-driven 3D Conversational Gestures from Video
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To this end, we apply state-of-the-art monocular approaches for 3D body and hand pose estimation as well as dense 3D face performance capture to the video corpus. ...
We also contribute a new way to create a large corpus of more than 33 hours of annotated body, hand, and face data from in-the-wild videos of talking people. ...
We make use of CMU Sphinx [26] for computing the coefficients, and use 13 MFC coefficients and an additional feature to account for the log mean energy of the input. ...
arXiv:2102.06837v1
fatcat:fea24vvphbh4jpuqzclfviq5fe
Automatic Behaviour Understanding in Medicine
2014
Proceedings of the 2014 Workshop on Roadmapping the Future of Multimodal Interaction Research including Business Opportunities and Challenges - RFMIR '14
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Perhaps one of the most promising areas is the application of automatic expressive behaviour understanding to help diagnose, monitor, and treat medical conditions that themselves alter a person's social ...
As Affective Computing and Social Signal Processing methods are becoming increasingly robust and accurate, novel areas of applications with significant societal impact are opening up for exploration. ...
In particular, I would like to thank Jeff Cohn, Amanda Williams, Stefan Scherer, LP Morency, Chris Hollis, Richard Morriss, Don Sharkey, David Daley, and mostly G van Londen, who started all this with ...
doi:10.1145/2666253.2666260
dblp:conf/icmi/Valstar14
fatcat:ea3jnmhs3rds7eg5dc6zb5i7gq
Face transfer with multilinear models
2005
ACM SIGGRAPH 2005 Papers on - SIGGRAPH '05
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Our Face Transfer learns a model of 3D facial geometry variations in order to infer a particular face shape from 2D images. ...
doi:10.1145/1186822.1073209
fatcat:ycfhzjzojfbzbhnor3mzu26om4
Face transfer with multilinear models
2005
ACM Transactions on Graphics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Our Face Transfer learns a model of 3D facial geometry variations in order to infer a particular face shape from 2D images. ...
doi:10.1145/1073204.1073209
fatcat:b4iidkieezff3gkmbdu6ozyvea
Face transfer with multilinear models
2006
ACM SIGGRAPH 2006 Courses on - SIGGRAPH '06
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Face Transfer offers new solutions to these problems and links the estimated model with a face-tracking algorithm to extract pose, expression, and viseme parameters. ...
Our Face Transfer learns a model of 3D facial geometry variations in order to infer a particular face shape from 2D images. ...
doi:10.1145/1185657.1185864
dblp:conf/siggraph/VlasicBPP06
fatcat:i62ikvmrk5ainlg7c4usbkdhjq
Towards a Multimedia Knowledge-Based Agent with Social Competence and Human Interaction Capabilities
2016
Proceedings of the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction - MARMI '16
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In contrast to most of the existing agents, the presented agent is aimed to have linguistic cultural, social and emotional competence needed to interact with elderly and migrants. ...
We present work in progress on an intelligent embodied conversation agent in the basic care and healthcare domain. ...
., elderly); they do not take into account cultural idiosyncrasies of the addressee when planning their actions; they are not multilingual to be able to intermediate between a migrant and a native from ...
doi:10.1145/2927006.2927011
dblp:conf/mir/WannerBDDLMSKVK16
fatcat:h5znrszjszcujenxbw7zl2w7ui
A shared neural encoding model for the prediction of subject-specific fMRI response
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In the present study, we propose a shared convolutional neural encoding method that accounts for individual-level differences. ...
We further demonstrate the ability of the shared encoding model to successfully capture meaningful individual differences in response to traditional task-based facial and scenes stimuli. ...
Specifically, we predict brain response to visual stimuli (comprising faces, places, tools and body parts) from the HCP Working Memory (WM) task and use the predicted response to synthesize face and scene ...
arXiv:2006.15802v2
fatcat:mizlivo55vdfrkkfbx2pf364ai
VR content creation and exploration with deep learning: A survey
2020
Computational Visual Media
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This article surveys recent research that uses such deep learning methods for VR content creation and exploration. ...
It originated in the 1960s and has evolved to provide increasing immersion, interactivity, imagination, and intelligence. ...
Acknowledgements The authors would like to thank the reviewers. This work was supported by the National Natural Science Foundation of China (Grant Nos. 61902012, 61932003). ...
doi:10.1007/s41095-020-0162-z
fatcat:lgogzx26bvhn5f7uyefjkz7zny
Evolving and breeding robots
[chapter]
1998
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
However, it is not enough to evolve controllers alone, and we argue that robot body plans and controllers should co-evolve, which leads to an alternative form of evolvable hardware. ...
Initially, we investigated simulation-reality relationships in order to transfer our articial life simulation work with evolution of neural network agents to real robots. ...
Materials and facilities were provided by the LEGO Group, the Danish National Centre for IT Research { CIT, the National Research Council, Rome, Italy, and the University o f Edinburgh. ...
doi:10.1007/3-540-64957-3_73
fatcat:3np6zxfaujcixf6i5vbd3re36q
Stretching tacit knowledge beyond a local fix? Global spaces of learning in advertising professional service firms
2006
Journal of Economic Geography
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
of organizational knowledge leverage -'knowledge transfer' in the form of best practice and 'the social production of new knowledge' -and their complementary yet differentiated roles in organizations ...
Scholars have, therefore, called for better understanding of the multiple geographies of knowledge through research of local but also global relational spaces of learning and the different types of knowledge ...
For example, Morgan (2004, 5) draws our attention to the well recognised fact that "body language and face-to-face communication convey as much as (if not more than) verbal communication". ...
doi:10.1093/jeg/lbi023
fatcat:egtvvz34snff3m4su224nugsai
Embracing the Agile Mindset: Faculty Perspective
2020
International Journal of Research Publications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It's about thinking through how one can understand what's going on in the environment, identify what uncertainty one is facing and figure out how to adapt and go along. ...
An agile mindset is about creating and responding to change in uncertain and turbulent environments. ...
Post-pandemic times could see a blend of e-learning and mainstream face-to-face teaching in Management Education. ...
doi:10.47119/ijrp1006511120201577
fatcat:f3cx5arjznapniyrpsst2n4yku
SVD Square-root Iterated Extended Kalman Filter for Modeling of Epileptic Seizure Count Time Series with External Inputs
2019
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper a nonlinear filtering algorithm for count time series is developed that takes the non-negativity of the data into account and preserves positive definiteness of the covariance matrices of ...
The resulting algorithm is applied to the evaluation and design of therapies for patients suffering from Myoclonic Astatic Epilepsy, employing time series of daily seizure rate. ...
based systems for face expressions in general. ...
doi:10.1109/embc.2019.8857159
pmid:31945973
fatcat:dmckhawdpbfwjoiekeerk4ra54
« Previous
Showing results 1 — 15 out of 7,341 results