<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Littlewort, G.</style></author><author><style face="normal" font="default" size="100%">Whitehill, J.</style></author><author><style face="normal" font="default" size="100%">Wu, T.</style></author><author><style face="normal" font="default" size="100%">Fasel, I.</style></author><author><style face="normal" font="default" size="100%">Frank, M.</style></author><author><style face="normal" font="default" size="100%">Movellan, J.</style></author><author><style face="normal" font="default" size="100%">Bartlett, M.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The computer expression recognition toolbox (CERT)</style></title><secondary-title><style face="normal" font="default" size="100%">2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshops (FG 2011)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">3D orientation</style></keyword><keyword><style  face="normal" font="default" size="100%">Accuracy</style></keyword><keyword><style  face="normal" font="default" size="100%">automatic real-time facial expression recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">CERT</style></keyword><keyword><style  face="normal" font="default" size="100%">computer expression recognition toolbox</style></keyword><keyword><style  face="normal" font="default" size="100%">Detectors</style></keyword><keyword><style  face="normal" font="default" size="100%">dual core laptop</style></keyword><keyword><style  face="normal" font="default" size="100%">Emotion recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Encoding</style></keyword><keyword><style  face="normal" font="default" size="100%">extended Cohn-Kanade</style></keyword><keyword><style  face="normal" font="default" size="100%">Face</style></keyword><keyword><style  face="normal" font="default" size="100%">face recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">facial action unit coding system</style></keyword><keyword><style  face="normal" font="default" size="100%">facial expression dataset</style></keyword><keyword><style  face="normal" font="default" size="100%">Facial features</style></keyword><keyword><style  face="normal" font="default" size="100%">FACS</style></keyword><keyword><style  face="normal" font="default" size="100%">Gold</style></keyword><keyword><style  face="normal" font="default" size="100%">Image coding</style></keyword><keyword><style  face="normal" font="default" size="100%">software tool</style></keyword><keyword><style  face="normal" font="default" size="100%">software tools</style></keyword><keyword><style  face="normal" font="default" size="100%">two-alternative forced choice task</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2011</style></year><pub-dates><date><style  face="normal" font="default" size="100%">03/2011</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Santa Barbara, CA</style></pub-location><isbn><style face="normal" font="default" size="100%">978-1-4244-9140-7</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p class=&quot;p1&quot;&gt;We present the Computer Expression Recognition Toolbox (CERT), a software tool for fully automatic real-time facial expression recognition, and officially release it for free academic use. CERT can automatically code the intensity of 19 different facial actions from the Facial Action Unit Coding System (FACS) and 6 different prototypical facial expressions. It also estimates the locations of 10 facial features as well as the 3-D orientation (yaw, pitch, roll) of the head. On a database of posed facial expressions, Extended Cohn-Kanade (CK+[1]), CERT achieves an average recognition performance (probability of correctness on a two-alternative forced choice (2AFC) task between one positive and one negative example) of 90.1% when analyzing facial actions. On a spontaneous facial expression dataset, CERT achieves an accuracy of nearly 80%. In a standard dual core laptop, CERT can process 320 × 240 video images in real time at approximately 10 frames per second.&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">12007742</style></accession-num></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Whitehill, J.</style></author><author><style face="normal" font="default" size="100%">Littlewort, G.</style></author><author><style face="normal" font="default" size="100%">Fasel, I.</style></author><author><style face="normal" font="default" size="100%">Bartlett, M.</style></author><author><style face="normal" font="default" size="100%">Movellan, J.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Toward Practical Smile Detection</style></title><secondary-title><style face="normal" font="default" size="100%">IEEE Transactions on Pattern Analysis and Machine Intelligence</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Artificial intelligence</style></keyword><keyword><style  face="normal" font="default" size="100%">Automated</style></keyword><keyword><style  face="normal" font="default" size="100%">automatic facial expression recognition research</style></keyword><keyword><style  face="normal" font="default" size="100%">Biological Pattern Recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Biometry</style></keyword><keyword><style  face="normal" font="default" size="100%">Computer simulation</style></keyword><keyword><style  face="normal" font="default" size="100%">Computer vision</style></keyword><keyword><style  face="normal" font="default" size="100%">Computer-Assisted</style></keyword><keyword><style  face="normal" font="default" size="100%">Face</style></keyword><keyword><style  face="normal" font="default" size="100%">Face and gesture recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">face recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">feature representation</style></keyword><keyword><style  face="normal" font="default" size="100%">human-level expression recognition accuracy</style></keyword><keyword><style  face="normal" font="default" size="100%">illumination conditions</style></keyword><keyword><style  face="normal" font="default" size="100%">Image databases</style></keyword><keyword><style  face="normal" font="default" size="100%">Image Enhancement</style></keyword><keyword><style  face="normal" font="default" size="100%">Image Interpretation</style></keyword><keyword><style  face="normal" font="default" size="100%">image registration image representation</style></keyword><keyword><style  face="normal" font="default" size="100%">learning (artificial intelligence)</style></keyword><keyword><style  face="normal" font="default" size="100%">machine learning approaches</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning Models</style></keyword><keyword><style  face="normal" font="default" size="100%">n Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">object detection</style></keyword><keyword><style  face="normal" font="default" size="100%">practical smile detection</style></keyword><keyword><style  face="normal" font="default" size="100%">Reproducibility of Results</style></keyword><keyword><style  face="normal" font="default" size="100%">Sensitivity and Specificity</style></keyword><keyword><style  face="normal" font="default" size="100%">Smiling</style></keyword><keyword><style  face="normal" font="default" size="100%">Subtraction Technique</style></keyword><keyword><style  face="normal" font="default" size="100%">training data set</style></keyword><keyword><style  face="normal" font="default" size="100%">visual databases</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">11/2009</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">31</style></volume><pages><style face="normal" font="default" size="100%">2106-2111</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style=&quot;color: rgb(68, 68, 68); font-family: 'Lucida Grande', Verdana, sans-serif; font-size: 14px;&quot;&gt;Machine learning approaches have produced some of the highest reported performances for facial expression recognition. However, to date, nearly all automatic facial expression recognition research has focused on optimizing performance on a few databases that were collected under controlled lighting conditions on a relatively small number of subjects. This paper explores whether current machine learning methods can be used to develop an expression recognition system that operates reliably in more realistic conditions. We explore the necessary characteristics of the training data set, image registration, feature representation, and machine learning algorithms. A new database, GENKI, is presented which contains pictures, photographed by the subjects themselves, from thousands of different people in many different real-world imaging conditions. Results suggest that human-level expression recognition accuracy in real-life illumination conditions is achievable with machine learning technology. However, the data sets currently used in the automatic expression recognition literature to evaluate progress may be overly constrained and could potentially lead research into locally optimal algorithmic solutions.&lt;/span&gt;&lt;/p&gt;
</style></abstract><issue><style face="normal" font="default" size="100%">11</style></issue><section><style face="normal" font="default" size="100%">2106</style></section></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Ruvolo, P.</style></author><author><style face="normal" font="default" size="100%">Whitehill, J.</style></author><author><style face="normal" font="default" size="100%">Virnes, M.</style></author><author><style face="normal" font="default" size="100%">Movellan, J.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Building a more effective teaching robot using apprenticeship learning</style></title><secondary-title><style face="normal" font="default" size="100%">7th IEEE International Conference on Development and Learning, 2008. ICDL 2008</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">apprenticeship learning</style></keyword><keyword><style  face="normal" font="default" size="100%">automated helicopter flight</style></keyword><keyword><style  face="normal" font="default" size="100%">Automatic control</style></keyword><keyword><style  face="normal" font="default" size="100%">Data mining</style></keyword><keyword><style  face="normal" font="default" size="100%">Delay</style></keyword><keyword><style  face="normal" font="default" size="100%">education</style></keyword><keyword><style  face="normal" font="default" size="100%">Educational robots</style></keyword><keyword><style  face="normal" font="default" size="100%">expert teaching</style></keyword><keyword><style  face="normal" font="default" size="100%">Helicopters</style></keyword><keyword><style  face="normal" font="default" size="100%">Human-robot interaction</style></keyword><keyword><style  face="normal" font="default" size="100%">humanoid robots</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans Learning systems</style></keyword><keyword><style  face="normal" font="default" size="100%">mechanical control</style></keyword><keyword><style  face="normal" font="default" size="100%">robot teaching</style></keyword><keyword><style  face="normal" font="default" size="100%">Robotics and Automation</style></keyword><keyword><style  face="normal" font="default" size="100%">RUBI social robot</style></keyword><keyword><style  face="normal" font="default" size="100%">time 18 month to 24 month</style></keyword><keyword><style  face="normal" font="default" size="100%">timing</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">08/2008</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">IEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Monterey, CA</style></pub-location><isbn><style face="normal" font="default" size="100%">978-1-4244-2661-4</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style=&quot;color: rgb(68, 68, 68); font-family: 'Lucida Grande', Verdana, sans-serif; font-size: 14px; background-color: rgba(0, 0, 0, 0.0470588);&quot;&gt;What defines good teaching? While attributes such as timing, responsiveness to social cues, and pacing of material clearly play a role, it is difficult to create a comprehensive specification of what it means to be a good teacher. On the other hand, it is relatively easy to obtain examples of expert teaching behavior by observing a real teacher. With this inspiration as our guide, we investigated apprenticeship learning methods [1] that use data recorded from expert teachers as a means of improving the teaching abilities of RUBI, a social robot immersed in a classroom of 18-24 month old children. While this approach has achieved considerable success in mechanical control, such as automated helicopter flight [2], until now there has been little work on applying it to the field of social robotics. This paper explores two particular approaches to apprenticeship learning, and analyzes the models of teaching that each approach learns from the data of the human teacher. Empirical results indicate that the apprenticeship learning paradigm, though still nascent in its use in the social robotics field, holds promise, and that our proposed methods can already extract meaningful teaching models from demonstrations of a human expert.&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">10367601</style></accession-num></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Whitehill, J.</style></author><author><style face="normal" font="default" size="100%">Movellan, Javier R.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A discriminative approach to frame-by-frame head pose tracking</style></title><secondary-title><style face="normal" font="default" size="100%">8th IEEE International Conference on Automatic Face Gesture Recognition, 2008. FG '08</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">accuracy drift</style></keyword><keyword><style  face="normal" font="default" size="100%">continuous video sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">controlled illumination condition</style></keyword><keyword><style  face="normal" font="default" size="100%">discriminative approach</style></keyword><keyword><style  face="normal" font="default" size="100%">face detection</style></keyword><keyword><style  face="normal" font="default" size="100%">face recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">facial appearance</style></keyword><keyword><style  face="normal" font="default" size="100%">frame-by-frame head pose tracking</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Image analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Image databases</style></keyword><keyword><style  face="normal" font="default" size="100%">Laboratories</style></keyword><keyword><style  face="normal" font="default" size="100%">Lighting</style></keyword><keyword><style  face="normal" font="default" size="100%">Magnetic heads</style></keyword><keyword><style  face="normal" font="default" size="100%">mean square error methods</style></keyword><keyword><style  face="normal" font="default" size="100%">pose estimation</style></keyword><keyword><style  face="normal" font="default" size="100%">Robustness</style></keyword><keyword><style  face="normal" font="default" size="100%">root-mean-square error tracking</style></keyword><keyword><style  face="normal" font="default" size="100%">System testing</style></keyword><keyword><style  face="normal" font="default" size="100%">Video sequences</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">09/2008</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Amsterdam</style></pub-location><isbn><style face="normal" font="default" size="100%">978-1-4244-2153-4</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style=&quot;color: rgb(68, 68, 68); font-family: 'Lucida Grande', Verdana, sans-serif; font-size: 14px; background-color: rgba(0, 0, 0, 0.0470588);&quot;&gt;We present a discriminative approach to frame-by-frame head pose tracking that is robust to a wide range of illuminations and facial appearances and that is inherently immune to accuracy drift. Most previous research on head pose tracking has been validated on test datasets spanning only a small (&amp;lt; 20) subjects under controlled illumination conditions on continuous video sequences. In contrast, the system presented in this paper was both trained and tested on a much larger database, GENKI, spanning tens of thousands of different subjects, illuminations, and geographical locations from images on the Web. Our pose estimator achieves accuracy of 5.82deg, 5.65deg, and 2.96deg root-mean-square (RMS) error for yaw, pitch, and roll, respectively. A set of 4000 images from this dataset, labeled for pose, was collected and released for use by the research community.&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">10571793</style></accession-num></record></records></xml>