<?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%">Butko, N.</style></author><author><style face="normal" font="default" size="100%">Theocharous, G.</style></author><author><style face="normal" font="default" size="100%">Philipose, 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%">Automated facial affect analysis for one-on-one tutoring applications</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%">automated facial affect analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">automated tutoring system</style></keyword><keyword><style  face="normal" font="default" size="100%">behavioural sciences computing</style></keyword><keyword><style  face="normal" font="default" size="100%">computer vision technique</style></keyword><keyword><style  face="normal" font="default" size="100%">Context</style></keyword><keyword><style  face="normal" font="default" size="100%">decision making</style></keyword><keyword><style  face="normal" font="default" size="100%">education</style></keyword><keyword><style  face="normal" font="default" size="100%">Emotion recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">face recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Human</style></keyword><keyword><style  face="normal" font="default" size="100%">human computer interaction</style></keyword><keyword><style  face="normal" font="default" size="100%">Labeling</style></keyword><keyword><style  face="normal" font="default" size="100%">Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Mood</style></keyword><keyword><style  face="normal" font="default" size="100%">n Histograms</style></keyword><keyword><style  face="normal" font="default" size="100%">one-on-one tutoring application</style></keyword><keyword><style  face="normal" font="default" size="100%">s Intelligent tutoring systems</style></keyword><keyword><style  face="normal" font="default" size="100%">student mood analysis</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&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;In this paper, we explore the use of computer vision techniques to analyze students' moods during one-on-one teaching interactions. The eventual goal is to create automated tutoring systems that are sensitive to the student's mood and affective state. We find that the problem of accurately determining a child's mood from a single video frame is surprisingly difficult, even for humans. However when the system is allowed to make decisions based on information from 10 to 30 seconds of video, excellent performance may be obtained.&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">12007758</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%">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>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Wu, T.</style></author><author><style face="normal" font="default" size="100%">Butko, N.</style></author><author><style face="normal" font="default" size="100%">Ruvulo, P.</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%">Learning to Make Facial Expressions</style></title><secondary-title><style face="normal" font="default" size="100%">IEEE 8th International Conference on Development and Learning, 2009. ICDL 2009</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Actuators</style></keyword><keyword><style  face="normal" font="default" size="100%">Emotion recognition</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 motor parameters</style></keyword><keyword><style  face="normal" font="default" size="100%">Feedback</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</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</style></keyword><keyword><style  face="normal" font="default" size="100%">Magnetic heads</style></keyword><keyword><style  face="normal" font="default" size="100%">Pediatrics</style></keyword><keyword><style  face="normal" font="default" size="100%">real-time facial expression recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Robot sensing systems</style></keyword><keyword><style  face="normal" font="default" size="100%">robotic head</style></keyword><keyword><style  face="normal" font="default" size="100%">Robots</style></keyword><keyword><style  face="normal" font="default" size="100%">self-guided learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Servomechanisms</style></keyword><keyword><style  face="normal" font="default" size="100%">Servomotors</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%">06/2009</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%">Shanghai</style></pub-location><isbn><style face="normal" font="default" size="100%">978-1-4244-4117-4</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;&quot;&gt;This paper explores the process of self-guided learning of realistic facial expression production by a robotic head with 31 degrees of freedom. Facial motor parameters were learned using feedback from real-time facial expression recognition from video. The experiments show that the mapping of servos to expressions was learned in under one-hour of training time. We discuss how our work may help illuminate the computational study of how infants learn to make facial expressions.&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">10801981</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%">Ruvolo, P.</style></author><author><style face="normal" font="default" size="100%">Fasel, I.</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%">Auditory mood detection for social and educational robots</style></title><secondary-title><style face="normal" font="default" size="100%">IEEE International Conference on Robotics and Automation, 2008. ICRA 2008</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">auditory mood detection</style></keyword><keyword><style  face="normal" font="default" size="100%">Computer vision</style></keyword><keyword><style  face="normal" font="default" size="100%">educational robot</style></keyword><keyword><style  face="normal" font="default" size="100%">Educational robots</style></keyword><keyword><style  face="normal" font="default" size="100%">Emotion recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">emotional speech database</style></keyword><keyword><style  face="normal" font="default" size="100%">face detection</style></keyword><keyword><style  face="normal" font="default" size="100%">hearing</style></keyword><keyword><style  face="normal" font="default" size="100%">interactive robotic application</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</style></keyword><keyword><style  face="normal" font="default" size="100%">Mood Prototypes</style></keyword><keyword><style  face="normal" font="default" size="100%">object recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">Robotics and Automation Robots</style></keyword><keyword><style  face="normal" font="default" size="100%">social mood</style></keyword><keyword><style  face="normal" font="default" size="100%">social robot</style></keyword><keyword><style  face="normal" font="default" size="100%">Speech</style></keyword><keyword><style  face="normal" font="default" size="100%">USA Councils</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%">05/2008</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%">Pasadena, CA</style></pub-location><isbn><style face="normal" font="default" size="100%">978-1-4244-1646-2</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;&quot;&gt;Social robots face the fundamental challenge of detecting and adapting their behavior to the current social mood. For example, robots that assist teachers in early education must choose different behaviors depending on whether the children are crying, laughing, sleeping, or singing songs. Interactive robotic applications require perceptual algorithms that both run in real time and are adaptable to the challenging conditions of daily life. This paper explores a novel approach to auditory mood detection which was born out of our experience immersing social robots in classroom environments. We propose a new set of low-level spectral contrast features that extends a class of features which have proven very successful for object recognition in the modern computer vision literature. Features are selected and combined using machine learning approaches so as to make decisions about the ongoing auditory mood. We demonstrate excellent performance on two standard emotional speech databases (the Berlin Emotional Speech [W. Burkhardt et al., 2005], and the ORATOR dataset [H. Quast, 2001]). In addition we establish strong baseline performance for mood detection on a database collected from a social robot immersed in a classroom of 18-24 months old children [J. Movellan er al., 2007]. This approach operates in real time at little computational cost. It has the potential to greatly enhance the effectiveness of social robots in daily life environments.&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">10014826</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%">Ruvolo, P.</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%">Automatic cry detection in early childhood education settings</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%">Acoustic noise</style></keyword><keyword><style  face="normal" font="default" size="100%">auditory moods</style></keyword><keyword><style  face="normal" font="default" size="100%">automatic cry detection</style></keyword><keyword><style  face="normal" font="default" size="100%">behavioural sciences computing</style></keyword><keyword><style  face="normal" font="default" size="100%">Deafness</style></keyword><keyword><style  face="normal" font="default" size="100%">early childhood education settings</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%">Emotion recognition</style></keyword><keyword><style  face="normal" font="default" size="100%">human coders</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</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</style></keyword><keyword><style  face="normal" font="default" size="100%">Mood</style></keyword><keyword><style  face="normal" font="default" size="100%">preschool classrooms</style></keyword><keyword><style  face="normal" font="default" size="100%">Prototypes</style></keyword><keyword><style  face="normal" font="default" size="100%">Robustness</style></keyword><keyword><style  face="normal" font="default" size="100%">Working environment noise</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%">IEEE</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;We present results on applying a novel machine learning approach for learning auditory moods in natural environments [1] to the problem of detecting crying episodes in preschool classrooms. The resulting system achieved levels of performance approaching that of human coders and also significantly outperformed previous approaches to this problem [2].&lt;/span&gt;&lt;/p&gt;
</style></abstract><accession-num><style face="normal" font="default" size="100%">10367600</style></accession-num></record></records></xml>