K
Kenji Watanabe
Researcher at National Institute of Advanced Industrial Science and Technology
Publications - 31
Citations - 177
Kenji Watanabe is an academic researcher from National Institute of Advanced Industrial Science and Technology. The author has contributed to research in topics: Linear discriminant analysis & Matrix decomposition. The author has an hindex of 7, co-authored 31 publications receiving 161 citations. Previous affiliations of Kenji Watanabe include Wakayama University & University of Tsukuba.
Papers
More filters
Journal ArticleDOI
Molecular dynamics of STAT3 on IL-6 signaling pathway in living cells.
Kenji Watanabe,Kenta Saito,Masataka Kinjo,Tadashi Matsuda,Mamoru Tamura,Shigeyuki Kon,Tadaaki Miyazaki,Toshimitsu Uede +7 more
TL;DR: It is found that STAT3 existed as a complex whose molecular weight was less than 400kDa before IL-6 addition, however, IL- 6 stimulation induced the formation of STAT3 dimer as a megacomplex form whose molecular Weight was more than 1MDa at the cytoplasm and a very slow diffusion complex in the nucleus.
Journal ArticleDOI
Logistic label propagation
TL;DR: This paper proposes a novel method for semi-supervised learning, called logistic label propagation (LLP), which employs the logistic function to classify input pattern vectors, similarly to logistic regression.
Journal Article
Automated Service Scene Detection for Badminton Game Analysis Using CHLAC and MRA
TL;DR: This paper describes an automatic serve scene detection method employing cubic higher-order local auto-correlation (CHLAC) and multiple regression analysis (MRA) and demonstrates the effectiveness of this method on video sequences of five badminton matches captured by a single ceiling camera.
Journal Article
Automated service scene detection for Badminton game analysis Using CHLAC and MRA
Journal ArticleDOI
Robust pruning for efficient CNNs
TL;DR: A pruning method based on a novel criterion to measure the redundancy of the parameters in CNNs through empirical classification loss that can provide stable metric for parameters and evaluate layers of various depth fairly without biases toward shallower or deeper layers is proposed.