Anomoulous/Exceptional Pattern Mining from Stream Data with Weak-Label Information

Japanese version

Grants-in-Aid for Scientific Research, Fundamental Research (B), 18H03290

Japan Society for the Promotion of Science (JSPS)

2018/4/1 - 2021/3/31

Research organization

Einoshin Suzuki

Principal investigator, Professor

Department of Informatics, ISEE, Kyushu University

Shin Ando

Co-investigator, Associate Professor

Department of Business Economics, School of Management, Tokyo University of Science

Research abstract:

Selected outcomes:
1. Soichiro Oura, Tetsu Matsukawa, Einoshin Suzuki: "Multimodal Deep Neural Network with Image Sequence Features for Video Captioning", Proc. 2018 International Joint Conference on Neural Networks (IJCNN 2018), pp. 3296-3302, Rio de Janeiro, July 2018. DOI ?
2. Kaikai Zhao, Tetsu Matsukawa, Einoshin Suzuki: "Retraining: A Simple Way to Improve the Ensemble Accuracy of Deep Neural Networks for Image Classification", Proc. 25th International Conference on Pattern Recognition (ICPR 2018), pp. ?-?, Beijing, August 2018 (accepted for publication). DOI ?