S
Shogo Okada
Researcher at Japan Advanced Institute of Science and Technology
Publications - 86
Citations - 584
Shogo Okada is an academic researcher from Japan Advanced Institute of Science and Technology. The author has contributed to research in topics: Artificial neural network & Cluster analysis. The author has an hindex of 12, co-authored 78 publications receiving 467 citations. Previous affiliations of Shogo Okada include Mitsubishi & Tokyo Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Unsupervised simultaneous learning of gestures, actions and their associations for Human-Robot Interaction
TL;DR: Human-Robot Interaction using free hand gestures is gaining more importance as more untrained humans are operating robots in home and office environments.
Proceedings ArticleDOI
Predicting Influential Statements in Group Discussions using Speech and Head Motion Information
TL;DR: It is discovered that the assessment of each participant in terms of discussion facilitation skills by experienced observers correlated highly to the number of influential utterances by a given participant, suggesting that the proposed model can predict influential statements with considerable accuracy, and the prediction results can be a good predictor of facilitators in group discussions.
Proceedings ArticleDOI
Estimating communication skills using dialogue acts and nonverbal features in multiple discussion datasets
Shogo Okada,Yoshihiko Ohtake,Yukiko I. Nakano,Yuki Hayashi,Hung-Hsuan Huang,Yutaka Takase,Katsumi Nitta +6 more
TL;DR: A regression model was developed to infer the score for communication skill using multi-modal features including linguistic and nonverbal features: prosodic, speaking turn, and head activity and the experimental results show that the multimodal fusing model with feature selection achieved the best accuracy.
Proceedings ArticleDOI
Personality Trait Classification via Co-Occurrent Multiparty Multimodal Event Discovery
TL;DR: Experimental results show that the model trained with co-occurrence features obtained higher accuracy than previously related work in 8 out of 10 traits, and the co-Occurrence features improve the accuracy from 2 % up to 17 %.
Proceedings ArticleDOI
Motion recognition based on Dynamic-Time Warping method with Self-Organizing Incremental Neural Network
Shogo Okada,O. Hasegawa +1 more
TL;DR: This paper presents an approach for recognition of motion (gesture) that is based on the Self-Organizing Incremental Neural Network (SOINN) and Dynamic Time Warping (DTW) and shows that SOINN-DTW outperforms HMM, CRF.