AUTHOR=Zhang Di , Chen Chen , Tan Fa , Qian Beibei , Li Wei , He Xuan , Lei Susan 

TITLE=Multi-view and multi-scale behavior recognition algorithm based on attention mechanism

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2023.1276208

DOI=10.3389/fnbot.2023.1276208

ISSN=1662-5218

ABSTRACT=Human behaviour recognition plays a crucial role in the field of smart education. It offers a nuanced understanding of teaching and learning dynamics by revealing the behaviours of both teachers and students. In this study, to address the exigencies of teaching behaviour analysis in smart education, we first constructed a teaching behaviour analysis dataset called EuClass. EuClass contains 13 types of teacher/student behaviour categories and provides multi-view, multi-scale video data for the research and practical applications of teacher/student behaviour recognition. We also provide a teaching behaviour analysis network containing an attention-based network and an intra-class differential representation learning module. The attention mechanism uses a two-level attention module encompassing spatial and channel dimensions. The intra-class differential representation learning module utilised a unified loss function to reduce the distance between features. Experiments conducted on the EuClass dataset and a widely used action/gesture recognition dataset, IsoGD, demonstrate the effectiveness of our method in comparison to current state-of-the-art methods, with the recognition accuracy increased by 1-2% on average.