Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
HCGSYMPO (2nd) |
2015-12-16 - 2015-12-18 |
Toyama |
Toyama International Conference Center |
Generation of facial expressions on 2D images of neutral face by impression transfer vector defined by SVM Haruna Yamaguchi, Yudai Arai, Yoshinori Inaba, Shigeru Akamatsu (Hosei Univ.) |
Faces play an important role in all facets of human communication, even in human-machine communications. Thus, creating ... [more] |
|
HCGSYMPO (2nd) |
2015-12-16 - 2015-12-18 |
Toyama |
Toyama International Conference Center |
Generation of 3D facial expressions by Impression Transfer Vector Method considering individual difference of the facial shape Yudai Arai, Horii Kazuya, Yoshinori Inaba, Shigeru Akamatsu (Hosei Univ.) |
Facial expressions play an important role in all facets of human communication, even in human-machine communications. On... [more] |
|
PRMU, BioX |
2015-03-19 16:40 |
Kanagawa |
|
Semi-Supervised Low-rank GMM Learning for Multimodal Distribution Eita Aoki, Tetsuya Matsumoto, Noboru Ohnishi (Nagoya Univ.) BioX2014-60 PRMU2014-180 |
In this study, we examine the learning method of each category distribution under underdetermined environment that categ... [more] |
BioX2014-60 PRMU2014-180 pp.129-134 |
IBISML |
2014-11-18 15:00 |
Aichi |
Nagoya Univ. |
[Poster Presentation]
Direct Estimation of the Derivative of Quadratic Mutual Information with Application in Sufficient Dimension Reduction Voot Tangkaratt (Tokyo Inst. of Tech.), Hiroaki Sasaki, Masashi Sugiyama (Univ. of Tokyo) IBISML2014-79 |
An accurate estimator of a function does not necessary mean that its derivative is an accurate estimator of the derivati... [more] |
IBISML2014-79 pp.329-336 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2014-09-01 16:30 |
Ibaraki |
|
Dimentionality Reduction Methods Using Error Correcting Codes for Feature Extraction Wataru Matsumoto, Genta Yoshimura, Takashi Yamazaki (Mitsubishi Electric) PRMU2014-46 IBISML2014-27 |
For various media retrieval and recognition applications, we consider the feature extraction vector compressed by a spar... [more] |
PRMU2014-46 IBISML2014-27 pp.81-84 |
SP |
2014-02-28 12:40 |
Tokushima |
The University of Tokushima |
[Poster Presentation]
Dimensionality Reduction of Feature Vector for Shouted Speech Detection in Noisy Environments Naoto Kakino, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.), Hiroaki Nanjo (Ryukoku Univ.) SP2013-111 |
In this study, we try to detect shouted speech uttered in the hazardous situation toward a crime prevention system with ... [more] |
SP2013-111 pp.21-22 |
HCGSYMPO (2nd) |
2013-12-18 - 2013-12-20 |
Ehime |
Matsuyama Multi-Purpose Community Cente |
Generation of facial expressions based on morphable 3D shape model
-- A trial of emphasizing perceived impressions between pairs of faces representing confusing expressions -- Yudai Arai, Syunsuke Nagata, Yoshinori Inaba, Shigeru Akamatsu (Hosei Univ.) |
In order to create 3D faces displaying facial expressions, transformation of the face shape from the original straight f... [more] |
|
IBISML |
2013-07-18 11:30 |
Tokyo |
Nishiwaseda Campus (Waseda univ.) |
Estimation of Local Coordinates in Low Dimensional Subspace based on Semi-Supervised Learning with Order Constraints
-- Local Coordinate Extraction from Optical Hyperspectral Data of Vegetation -- Kuniaki Uto (Tokyo Tech.) IBISML2013-5 |
We propose a new method, semi-supervised manifold coordinate projection under order constraints (SMCPOC), and the two va... [more] |
IBISML2013-5 pp.27-34 |
IBISML |
2013-07-18 14:20 |
Tokyo |
Nishiwaseda Campus (Waseda univ.) |
Detection of abnormal data based on linear classifiers using local coordinates on a normal class
-- Tree disease detection in hyperspectral forest images -- Kuniaki Uto (Tokyo Tech.) IBISML2013-8 |
We propose a new linear classification method in the framework of the generalized eigenvalue problem in which the singul... [more] |
IBISML2013-8 pp.51-58 |
HCGSYMPO (2nd) |
2012-12-10 - 2012-12-12 |
Kumamoto |
Kumamoto-Shintoshin-plaza |
Generation of Facial Expressions for Novel Face Based on PCA of the 3D Shape Data Representing Various Facial Expressions Marie Amaki, Chisa Watanabe, Syunsuke Nagata, Syunta Yamamoto, Yoshinori Inaba, Shigeru Akamatsu (Hosei Univ.) |
In order to create 3D face models displaying facial expressions, transformation of the original model representing a str... [more] |
|
IBISML |
2012-03-13 16:30 |
Tokyo |
The Institute of Statistical Mathematics |
Feature Selection via L1-Penalized Squared-Loss Mutual Information Wittawat Jitkrittum, Hirotaka Hachiya, Masashi Sugiyama (Tokyo Inst. of Tech.) IBISML2011-107 |
Feature selection is a technique to screen out less important features.
Many existing supervised feature selection alg... [more] |
IBISML2011-107 pp.139-146 |
SANE |
2011-06-23 16:10 |
Ibaraki |
Tsukuba Space Center (JAXA) |
Proposal of A Telemetry Data Monitoring Method Using Dimensionality Reduction Techniques Takehisa Yairi, Takaaki Tagawa (Univ. of Tokyo), Noboru Takata (JAXA), Yukihito Yamaguchi, Yuuzou Tomabechi, Teppei Matsubara, Yuuji Bessho, Takahiro Tanaka, Youko Nishimoto (TIS) SANE2011-27 |
Authors are developing an advanced health monitoring / anomaly detection method for spacecraft systems using machine lea... [more] |
SANE2011-27 pp.59-64 |
SIS |
2011-06-09 10:40 |
Okinawa |
Ishigaki Health & Wellness Center |
Stress state classification based on photoplethysmogram by supervised dimensionally reduction Ying Li, Keiichi Horio (Kyushu Inst. of Tech.) SIS2011-3 |
In this paper, we introduce a latent variables extraction method to improve a classification of stress states. Features ... [more] |
SIS2011-3 pp.11-14 |
CQ, MVE, IE (Joint) [detail] |
2011-03-07 09:55 |
Nagasaki |
Yasuragi IOUJIMA |
Generation of Facial Expressions from Morphable 3D Face Model
-- Contribution of each PCA Parameter toward generation of arbitrary facial expressions -- Hirotoshi Inomata, Syunta Yamamoto, Yoshinori Inaba, Shigeru Akamatsu (Hosei Univ.) IE2010-162 MVE2010-150 |
Generation of arbitrary facial expressions to 3D face model has been usually achieved by either manual processing of the... [more] |
IE2010-162 MVE2010-150 pp.95-100 |
NLP |
2010-07-12 11:55 |
Ishikawa |
Ishikawa Prefectural Bunkyo Hall |
Analysis Using Space Embedded Equation in Moment Vector Space for High-dimensional Nonlinear System Hideki Satoh (Future Univ. Hakodate) NLP2010-33 |
A space embedded equation (SEE) has been developed for expressing an arbitrary high-dimensional target system as a low-d... [more] |
NLP2010-33 pp.23-28 |
COMP |
2010-03-12 09:40 |
Tokyo |
National Institute of Informatics |
Bayesian Joint Optimization for Matrix Factorization and Clustering Tikara Hosino (Nihon Unisys, Ltd.) COMP2009-50 |
Statistical clustering is the method for dividing the given samples by assumed distributions.
In high dimensional probl... [more] |
COMP2009-50 pp.9-12 |
PRMU |
2009-02-20 09:30 |
Tokyo |
Univ. of Tokyo (IIS) |
Document Classification by Local Fisher Discriminant Analysis Masashi Sugiyama (Tokyo Inst. of Tech.) PRMU2008-225 |
Dimensionality reduction is one of the important preprocessing steps
in practical pattern recognition.
SEmi-supervised... [more] |
PRMU2008-225 pp.103-108 |
SP |
2008-07-17 - 2008-07-19 |
Iwate |
Iwate Prefectural Univ. |
Dimensionality Reduction in Rescoring Using Likelihood Patterns Given by HMMs Tetsuji Ogawa, Tetsunori Kobayashi (Waseda Univ.) SP2008-55 |
We investigate dimensionality reduction of feature vectors in rescoring using likelihood patterns given by HMMs with lon... [more] |
SP2008-55 pp.73-78 |
DE |
2007-07-03 14:00 |
Miyagi |
Akiu hot springs (Sendai) |
Dimensionality Reduction via Latent Dirichlet Allocation for Document Clustering Tomonari Masada, Senya Kiyasu, Sueharu Miyahara (Nagasaki Univ.) DE2007-85 |
In this paper, we employ the latent Dirichlet allocation as a method for the dimensionality reduction
of feature vector... [more] |
DE2007-85 pp.381-386 |
IN |
2007-02-01 16:20 |
Aichi |
Aichi Prefectural University |
[Invited Talk]
Dimensionality reduction of Markov chains with applications in size-based task assignment with cycle stealing Takayuki Osogami (IBM Tokyo Research Lab.) IN2006-168 |
Multi-server systems are popular due to their scalability and cost effectiveness. To fully utilize a multi-server syste... [more] |
IN2006-168 pp.35-40 |