#discaas

[yukimat-research]

Multimodal Recording System for Collecting Facial and Postural Data in a Group Meeting

27th International Conference on Computers in Education (ICCE '19), pp.466-471, Kenting, Taiwan, December 4-6, 2019. Yusuke Soneda, Yuki Matsuda, Yutaka Arakawa and Keiichi Yasumoto

Abstract: By the spread of active learning and group work, the ability to collaborate and discuss among the participants becomes more important than before. Although several studies have reported on that micro facial expressions and body movements give psychological effects to others during conversation, most of them are lacking in quantitative evaluation and there are few datasets about group discussion. In this research, we proposed a highly reproducible system that helps to make datasets of group discussions with multiple devices such as an omnidirectional camera (360-degree camera), an eye tracker and a motion sensor. Our system operates those devices in one-stop to realizing synchronized recording. To confirm the feasibility, we built the proposed system with an omnidirectional camera, 4 eye trackers, and 4 motion sensors. Finally, we succeeded to make a dataset by recording 8 times group meeting by using our developed system easily.

Conference: http://ilt.nutn.edu.tw/icce2019/

[yukimat-research]

M3B Corpus: Multi-Modal Meeting Behavior Corpus for Group Meeting Assessment

Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '19 Adjunct, HASCA Workshop), pp.825-834, London, United Kingdom, September 10, 2019. Yusuke Soneda, Yuki Matsuda, Yutaka Arakawa and Keiichi Yasumoto

Abstract: This paper is the first trial to create a corpus on human-to-human multi-modal communication among multiple persons in group discussions. Our corpus includes not only video conversations but also the head movement and eye gaze. In addition, it includes detailed labels about the behaviors appeared in the discussion. Since we focused on the micro-behavior, we classified the general behavior into more detailed behaviors based on those meaning. For example, we have four types of smile: response, agree, interesting, sympathy. Because it takes much effort to create such corpus having multiple sensor data and detailed labels, it seems that no one has created it. In this work, we first attempted to create a corpus called ''M3B Corpus (Multi-Modal Meeting Behavior Corpus),'' which includes 320 minutes discussion among 21 Japanese students in total by developing the recording system that can handle multiple sensors and 360-degree camera simultaneously and synchronously. In this paper, we introduce our developed recording system and report the detail of M3B Corpus.

Conference (HASCA): http://hasca2019.hasc.jp/

Conference (UbiComp): http://ubicomp.org/ubicomp2019/

ACM Digital Library: https://doi.org/10.1145/3341162.3345588

PDF: https://dl.acm.org/doi/pdf/10.1145/3341162.3345588