Talking Detection In Collaborative Learning Environments
This work addresses the specific challenge of identifying talking instances and speakers in educational videos, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting talking activities in collaborative learning videos by using head detection and optical flow projections, achieving an overall accuracy of 59%, which outperforms Temporal Segment Network (42%) and Convolutional 3D (45%).
We study the problem of detecting talking activities in collaborative learning videos. Our approach uses head detection and projections of the log-magnitude of optical flow vectors to reduce the problem to a simple classification of small projection images without the need for training complex, 3-D activity classification systems. The small projection images are then easily classified using a simple majority vote of standard classifiers. For talking detection, our proposed approach is shown to significantly outperform single activity systems. We have an overall accuracy of 59% compared to 42% for Temporal Segment Network (TSN) and 45% for Convolutional 3D (C3D). In addition, our method is able to detect multiple talking instances from multiple speakers, while also detecting the speakers themselves.