Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] |
2022-06-27 17:50 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Comparison of Variational Bayes and Gibbs Sampling for Normal Inverse Gaussian Mixture Models Takashi Takekawa (Kogakuin Univ.) NC2022-9 IBISML2022-9 |
Mixture models for multivariate normal distributions (GMM) are widely used for data clustering. To compensate for the s... [more] |
NC2022-9 IBISML2022-9 pp.76-79 |
IBISML |
2022-03-09 14:55 |
Online |
Online |
Infinite SCAN: Joint Estimation of Changes and the Number of Word Senses with Gaussian Markov Random Fields Seiichi Inoue, Mamoru Komachi (TMU), Toshinobu Ogiso (NINJAL), Hiroya Takamura (AIST), Daichi Mochihashi (ISM) IBISML2021-47 |
In this study, we propose a hierarchical Bayesian model that can automatically estimate the number of senses for each wo... [more] |
IBISML2021-47 pp.61-68 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Generalized Dirichlet-Process-Means with f-Mean and Analysis of Influence Function Masahiro Kobayashi, Kazuho Watanabe (Toyohashi Tech.) IBISML2018-50 |
DP-means clustering was obtained as an extension of $K$-means clustering. While it is implemented with a simple and effi... [more] |
IBISML2018-50 pp.45-52 |
PRMU |
2013-06-10 13:30 |
Tokyo |
|
Topic Models Taking into Account Burstiness of Local Features in Video Yang Xie, Koji Eguchi (Kobe Univ.) PRMU2013-20 |
In this paper we propose a topic model, Corr-DCMLDA, which can integrate visual words and the corresponding speech trans... [more] |
PRMU2013-20 pp.5-10 |
IBISML |
2013-03-05 14:35 |
Aichi |
Nagoya Institute of Technology |
* Yusuke Kishi, Takuma Nakamura, Tatsuhiro Harada, Takashi Matsumoto (Waseda Univ.) IBISML2012-105 |
Infinite Hidden Markov Random Fields have been proposed for image segmentation as a solution to the problem of automatic... [more] |
IBISML2012-105 pp.87-94 |
AI |
2012-11-26 16:20 |
Fukuoka |
|
Human Behavior Process Extraction from the Web Masami Takahashi, Shin-ya Sato, Masato Matsuo (NTT) AI2012-20 |
The ability to understand our daily behaviors has long been regarded as enabling a variety of useful applications.
Pre... [more] |
AI2012-20 pp.31-35 |
IBISML |
2012-11-07 15:30 |
Tokyo |
Bunkyo School Building, Tokyo Campus, Tsukuba Univ. |
Nested-Hierarchical Dirichlet Process Mixtures for Simultaneous Document-Topic Clustering Shoji Tominaga, Masamichi Shimosaka, Rui Fukui, Tomomasa Sato (Univ. of Tokyo) IBISML2012-56 |
In this paper, we propose a nonparametric Bayesian framework for natural language processing (NLP). Our framework is bas... [more] |
IBISML2012-56 pp.157-164 |
SIS, IPSJ-AVM |
2012-09-20 12:50 |
Osaka |
Tottori Pref. Osaka Office |
Huge Flow Detection in Crowded Scenes using Dependent Dirichlet Process HMM Takuya Okamoto, Katsuya Kondo (Tottori Univ.) SIS2012-20 |
In this report, we present the framework of huge flow detection in crowded scenes. The flow analysis is done by using De... [more] |
SIS2012-20 pp.23-28 |
IBISML |
2012-03-12 11:25 |
Tokyo |
The Institute of Statistical Mathematics |
Fully Bayesian speaker clustering based on hierarchical structured Dirichlet process mixture model Naohiro Tawara, Tetsuji Ogawa (Waseda Univ.), Shinji Watanabe (NTT/MERL), Atsushi Nakamura (NTT), Tetsunori Kobayashi (Waseda Univ.) IBISML2011-90 |
We proposed a novel speaker clustering method by estimating the structure of a fully Bayesian utterance generative model... [more] |
IBISML2011-90 pp.21-28 |
PRMU, FM |
2011-12-16 16:30 |
Shizuoka |
Hamamatsu Campus, Shizuoka Univ. |
Nonparametric Bayesian State Estimation by Detecting Change Points and Sharing Segments on Time Series Data Masamichi Shimosaka, Yuichi Moriya, Rui Fukui, Tomomasa Sato (Univ. of Tokyo) PRMU2011-145 |
In this paper, we propose a novel framework for estimating state spaces where the size is unknown. The proposed framewor... [more] |
PRMU2011-145 pp.119-124 |
IBISML |
2011-11-10 15:45 |
Nara |
Nara Womens Univ. |
Clustering and planning for 3D near-infrared sensor data by Hierarchical Dirichlet Process Takayuki Shimotomai, Hiroyuki Okada, Takashi Omori (Tamagawa Univ.) IBISML2011-86 |
Using Chinese Restaurant Process that is one of Dirichlet process, we proposed and devloped a real robot system. We esti... [more] |
IBISML2011-86 pp.297-299 |
IBISML |
2010-11-05 15:30 |
Tokyo |
IIS, Univ. of Tokyo |
[Poster Presentation]
Infinite Latent Harmonic Allocation based on Hierarchical Dirichlet Process for Music Signal Analysis Kazuyoshi Yoshii, Masataka Goto (AIST) IBISML2010-86 |
This paper presents a method called the infinite latent harmonic allocation (iLHA) for detecting multiple fundamental fr... [more] |
IBISML2010-86 pp.195-202 |
IBISML |
2010-06-15 09:30 |
Tokyo |
Takeda Hall, Univ. Tokyo |
[Invited Talk]
Statistical Machine Learning Based on Nonparametric Bayesian Models Takaki Makino (Univ. of Tokyo.) IBISML2010-14 |
Nonparametric Bayesian models are a new approach for machine learning, involving overfitting avoidance and model selecti... [more] |
IBISML2010-14 pp.87-94 |
NC, MBE (Joint) |
2010-03-10 13:20 |
Tokyo |
Tamagawa University |
ARMA Model Based Time Series Clustering Using Dirichlet Process Mixture Models Yuki Washizu, Nobuo Suematsu, Akira Hayashi, Kazunori Iwata (Hiroshima City Univ) NC2009-135 |
Dirichlet Process Mixture (DPM) models allow nonparametric mixture modeling in which the number of mixture components is... [more] |
NC2009-135 pp.279-284 |
NC, MBE (Joint) |
2010-03-11 09:25 |
Tokyo |
Tamagawa University |
Correlated clustering model with hierarchical Dirichlet process Shunsuke Bamba, Toshiyuki Tanaka (Kyoto Univ.) NC2009-143 |
In the case of clustering with a Dirichlet process mixture model, underlying attributes which characterize clusters are ... [more] |
NC2009-143 pp.327-332 |
PRMU |
2009-03-13 10:45 |
Miyagi |
Tohoku Institute of Technology |
[Special Talk]
Implementations of Bayesian Learning
-- MCMC/SMC/DPEM -- Takashi Matsumoto (Waseda Univ.) PRMU2008-246 |
Several implementation schemes are reviewed for Bayesian learning. [more] |
PRMU2008-246 pp.39-42 |
PRMU |
2009-03-13 15:50 |
Miyagi |
Tohoku Institute of Technology |
Semi-supervised learning scheme using Dirichlet process EM-algorithm Tomoaki Kimura, Yohei Nakada (Waseda Univ.), Arnaud Doucet (ISM), Takashi Matsumoto (Waseda Univ.) PRMU2008-251 |
Learning with dataset which contains both labeled data and unlabeled data
is often called semi-supervised learning pro... [more] |
PRMU2008-251 pp.77-82 |
PRMU |
2009-02-20 10:00 |
Tokyo |
Univ. of Tokyo (IIS) |
Maximum A Posteriori Estimation For Dirichlet Process Language Models Takaaki Tokuda, Tomoaki Kimura, Yohei Nakada, Takashi Matsumoto (Waseda Univ.) PRMU2008-226 |
In recent years, Mixture distributions with Dirichlet Process (DP) prior have been successfully applied to many practica... [more] |
PRMU2008-226 pp.109-114 |
PRMU, DE |
2007-06-29 13:30 |
Hokkaido |
Hokkaido Univ. |
Graph Clustering with a Nonparametric Bayes Model Shuhei Kuwata, Naonori Ueda, Takeshi Yamada (NTT) DE2007-15 PRMU2007-41 |
We propose a new graph clustering method based on a nonparametric Bayesian model. Recently, Newman et al. proposed an ef... [more] |
DE2007-15 PRMU2007-41 pp.81-86 |
NC |
2006-10-11 13:00 |
Nara |
NAIST |
[Invited Talk]
Bayesian approaches in Natural Language Processing Daichi Mochihashi (ATR/NICT) |
This paper overviews Bayesian approaches in natural language processing
that are becoming prominent.
Without any knowl... [more] |
NC2006-49 pp.25-30 |