FEATURE FUSION OF FACE AND BODY FOR ENGAGEMENT INTENSITY DETECTION

Online learning has grown rapidly in recent years. Automatically detecting student engagement plays a vital role in gauging the learning progress of each student. In this paper we propose a novel approach to detect student engagement. We fuse facial and body features into a single long short-term memory (LSTM) model to detect the temporal dynamics of student engagement. In contrast to other CNN models that use only facial or body features, we enhance detection accuracy with a compact feature set by merging facial and body features. Our single model generates state-of-the-art results on an engagement database from the EmotiW 2018 Challenge, where it achieves a 0.0439 mean squared error on the validation set, competitive with ensemble methods.