Our research on facial expression analysis during group meetings has been accepted by MDPI Sensors.
DisCaaS: Micro Behavior Analysis on Discussion by Camera as a Sensor
In this study, we use a 360-degree camera to capture the facial expressions of participants during group meetings and classify them as nodding, smiling, speaking, etc. We started collecting group meeting videos in 2018 and are now collecting data on online video conferencing as well.
This research is the result of a basic analysis of the data collected so far, and was conducted in collaboration with DFKI (Research Center for Artificial Intelligence) in Germany and Nara Institute of Science and Technology.
DisCaaS: Micro Behavior Analysis on Discussion by Camera as a Sensor Journal Article
In: Sensors, vol. 21, no. 17, 2021, ISSN: 1424-8220.
Related research in our group
頷きのリアルタイムフィードバックによるビデオ会議支援手法の提案 Conference
情報処理学会DICOMOシンポジウム, 2021.
グループミーティング動画からの発話量抽出手法の検討 Conference
情報処理学会第82回全国大会, 2020.
ミーティング映像からの発話およびマイクロ動作識別手法 Conference
情報処理学会第65回ユビキタスコンピューティングシステム (UBI) 研究発表会, 2020.
Multimodal Recording System for Collecting Facial and Postural Data in a Group Meeting Proceedings Article
In: The 27th International Conference on Computers in Education (ICCE 2019), 2019.
M3B Corpus: Multi-Modal Meeting Behavior Corpus for Group Meeting Assessment Proceedings Article
In: The 7th International Workshop on Human Activity Sensing Corpus and Applications (HASCA2019), pp. 825–834, ACM, 2019.