ABSTRACT
Analyzing students' emotions from classroom videos can help both teachers and parents quickly know the engagement of students in class. The availability of high-definition cameras creates opportunities to record class scenes. However, watching videos is time-consuming, and it is challenging to gain a quick overview of the emotion distribution and find abnormal emotions. In this article, we propose EmotionCues, a visual analytics system to easily analyze classroom videos from the perspective of emotion summary and detailed analysis, which integrates emotion recognition algorithms with visualizations. It consists of three coordinated views: a summary view depicting the overall emotions and their dynamic evolution, a character view presenting the detailed emotion status of an individual, and a video view enhancing the video analysis with further details. Considering the possible inaccuracy of emotion recognition, we also explore several factors affecting the emotion analysis, such as face size and occlusion. They provide hints for inferring the possible inaccuracy and the corresponding reasons. Two use cases and interviews with end users and domain experts are conducted to show that the proposed system could be useful and effective for analyzing emotions in the classroom videos.
Subject(s)
Emotions/classification , Facial Expression , Image Processing, Computer-Assisted/methods , Schools , Video Recording/methods , Algorithms , Child , Humans , StudentsABSTRACT
The autoionization state of barium was observed by optics heterodyne between three-photon resonant nondegenerated six-wave mixing (NSWM) and two-photon resonant nondegenerated four-wave mixing (NFWM). In this way, optics heterodyne spectrum of 6p(3/2) 19d autoionization state of barium was measured. The suppression and enhancement of the NFWM signal was observed which was caused by the quantum interference between NFWM and NSWM. Our method is a pure nonlinear optic technique. It has the advantages of excellent spatial signal resolution and simple optical alignment. Here two-photon resonant NFWM is used as local oscillation, while three-photon resonant NSWM signal is used as signal beam. Detection of autoionization states of Ba was achieved by changing the frequency of signal beam. The phase matching condition of this technique is not so stringent and can be achieved over a very wide frequency range, which is very difficult in the general six-wave mixing. Furthermore, the signal is coherent light. Optics heterodyne spectrum is a Doppler-free spectroscopy when the incident lasers have narrow bandwidths.
