Learn More
We propose a method to automatically detect emotions in unconstrained settings as part of the 2013 Emotion Recognition in the Wild Challenge [16], organized in conjunction with the ACM International Conference on Multimodal Interaction (ICMI 2013). Our method combines multiple visual descriptors with paralinguistic audio features for multimodal(More)
Student-teacher verbal communication contributes to successful learning outcomes. In this study we explore the use of conceptual-based recurrence plots to characterize the dynamics of student-teacher interaction. The results indicate: 1) Individual differences in teachers' speech styles 2) Teacher speech may reflect strategies that are sensitive to student(More)
The overarching goal of this project is to develop computational models of the nonverbal behavior and interactive strategies observed during face-to-face teaching. This project will help advance the science of learning and teaching by improving our understanding of the dynamics of nonverbal behavior in teaching at a computational level across multiple(More)
BACKGROUND We assessed whether a high-resolution impedance manometry (HRIM) metric, bolus flow time (BFT) across the esophagogastric junction (EGJ), was abnormal in achalasia patients subtyped by the Chicago Classification and compared BFT to other HRM metrics. METHODS HRIM studies were performed in 60 achalasia patients (14 type I, 36 type II and 10 type(More)
  • 1