Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
MBE, NC (Joint) |
2017-03-13 10:25 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Estimation of the change of agent's behavior strategy using state-action history Shihori Uchida, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) NC2016-65 |
Reinforcement learning (RL) is a model of learning process of animals and intelligent agents to obtain the optimal behav... [more] |
NC2016-65 pp.7-12 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS (Joint) [detail] |
2015-06-23 16:35 |
Okinawa |
Okinawa Institute of Science and Technology |
Inverse reinforcemnet learing based on behaviors of a learning agent Shunsuke Sakurai, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) IBISML2015-15 |
An appropriate design of reward function is important for reinforcement learning to efficiently obtain an optimal policy... [more] |
IBISML2015-15 pp.95-99 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS (Joint) [detail] |
2015-06-25 09:55 |
Okinawa |
Okinawa Institute of Science and Technology |
Computational Complexity Reduction for Functional Connectivity Estimation in Large Scale Neural Network JeongHun Baek, Shigeyuki Oba (Kyoto Univ.), Junichiro Yoshimoto, Kenji Doya (OIST), Shin Ishii (Kyoto Univ.) IBISML2015-22 |
Identification of functional connectivity between neurons is an important issue in computational neu- roscience. Recentl... [more] |
IBISML2015-22 pp.181-185 |
NC, MBE |
2015-03-17 14:35 |
Tokyo |
Tamagawa University |
Registration of functional brain images using diffusion tensor image Takuya Fuchigami (Kyoto Univ.), Manabu Shikauchi (ATR), Yumi Shikauchi, Ken Nakae, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) MBE2014-158 NC2014-109 |
To register functionally activated brain areas, we propose to use diffusion tensor image (DTI), because a subject's area... [more] |
MBE2014-158 NC2014-109 pp.233-237 |
IBISML |
2015-03-06 15:15 |
Kyoto |
Kyoto University |
Recognition of daily-life actions by machine learning methods Yu Kodama, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) IBISML2014-95 |
In recent years, many researchers in computer vision are interested in human action recognition, whose improvement would... [more] |
IBISML2014-95 pp.73-78 |
NC, MBE (Joint) |
2014-03-18 14:00 |
Tokyo |
Tamagawa University |
Fusion of Multiple Cues from Color and Depth Domains using Occlusion Aware Bayesian Tracker Kourosh Meshgi, Shin-ichi Maeda, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) NC2013-110 |
[more] |
NC2013-110 pp.127-132 |
NC, MBE (Joint) |
2014-03-17 16:00 |
Tokyo |
Tamagawa University |
Co-adaptation for BMI helicopter control Shunsuke Sakurai, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) NC2013-129 |
Our goal is to design a Brain-Machine-Interface (BMI) system to enable humans to control complex machines through brain ... [more] |
NC2013-129 pp.233-238 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2013-09-02 17:30 |
Tottori |
|
Enhancing Probabilistic Appearance-Based Object Tracking with Depth Information
-- Object Tracking under Occlusion -- Kourosh Meshgi, Yu-zhe Li, Shigeyuki Oba, Shin-ichi Maeda, Shin Ishii (Kyoto Univ.) PRMU2013-42 IBISML2013-22 |
Object tracking has attracted recent attention because of high demands for its everyday-life applications. Handling occl... [more] |
PRMU2013-42 IBISML2013-22 pp.85-91 |
NC, MBE (Joint) |
2011-03-08 14:35 |
Tokyo |
Tamagawa University |
Improved Granger causality tests for network structure estimation from time-series data Hikaru Harima, Shigeyuki Oba, Shin Ishii (Kyoto Univ.) NC2010-178 |
Granger causality and its variants have been proposed for estimating network structure as a causality graph based on cor... [more] |
NC2010-178 pp.301-306 |
IBISML |
2010-06-15 10:25 |
Tokyo |
Takeda Hall, Univ. Tokyo |
[Invited Talk]
Statistical testing with large multiplicity Shigeyuki Oba (Kyoto Univ./JST) IBISML2010-15 |
Statistical hypothesis testing is a basic tool in
broad areas of scientific studies
and guarantees that an assertion... [more] |
IBISML2010-15 pp.95-102 |
NC, MBE (Joint) |
2010-03-11 15:00 |
Tokyo |
Tamagawa University |
Influence of inhibition of return in dynamic properties of visual attention Shinji Hotta (Kyoto Univ.), Shigeyuki Oba (Kyoto Univ./JST), Shin Ishii (Kyoto Univ.) NC2009-153 |
Visual attention tends to avoid locations where past visual attention has once focused. This phenomenon is called inhibi... [more] |
NC2009-153 pp.385-390 |
NC |
2009-01-19 11:45 |
Hokkaido |
Hokkaido Univ. |
A probabilistic model of maximum margin matrix factorization with ARD prior Masahiro Furuya (Nara Inst. of Scie and Tech), Shigeyuki Oba (Kyoto Univ.), Shin Ishii (Nara Inst.of Scie and Tech/Kyoto Univ.) NC2008-85 |
Various methods for missing value estimation of matrix data have been proposed based on low-rank approximation of matrix... [more] |
NC2008-85 pp.19-24 |
NC, NLP |
2008-06-26 13:50 |
Okinawa |
University of the Ryukyus |
Differential gene detection incorporating individual characters of samples and multiplicity of test Shigeyuki Oba, Shin Ishii (Kyoto Univ.) NLP2008-3 NC2008-13 |
For better detection of significant genes with differential expression (DE) between different clinical groups based on m... [more] |
NLP2008-3 NC2008-13 pp.13-18 |
NC, MBE (Joint) |
2008-03-13 16:00 |
Tokyo |
Tamagawa Univ |
A better estimation of ODP statistic in multiple simultaneous hypotheses testing Hiroto Nomura, Shigeyuki Oba (NAIST), Shin Ishii (Kyoto Univ.) NC2007-174 |
Detection of differentially expressed (DE) genes between different conditions of sample cells is a basic and fundamental... [more] |
NC2007-174 pp.367-372 |
NC |
2008-01-16 13:50 |
Hokkaido |
Centennial Hall, Hokkaido Univ. |
DETECTION OF MULTIPLE OVERLAPPING STRING-SHAPED OBJECTS FROM REAL IMAGES Clare Maeda, Shigeyuki Oba (NAIST), Naoto Yukinawa, Shin Ishii (Kyoto Univ.) NC2007-106 |
This study presents an image segmentation method for string-shaped objects which may overlap each other in a single imag... [more] |
NC2007-106 pp.115-120 |
NLP |
2005-11-18 15:00 |
Fukuoka |
Kyushu Institute of Technology |
A Selection Criterion for Robust Classifiers by Considering the Variance of Test Performance Ikumi Suzuki, Shigeyuki Oba, Junichiro Hirayama, Shin Ishii (NAIST) |
In classification problems with gene expression profiles emerged from clinical field, we usually compare performances of... [more] |
NLP2005-66 pp.25-30 |