Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 09:00 |
Fukuoka |
Fukuoka Univ. |
Sequential Pattern Recognition by Local Classifiers and Dynamic Time Warping Masahiro Fukutomi, Koichi Ogawara, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) PRMU2010-77 IBISML2010-49 |
This paper describes a method for recognizing sequential patterns with nonlinear time warping. The proposed method uses ... [more] |
PRMU2010-77 IBISML2010-49 pp.157-164 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 09:30 |
Fukuoka |
Fukuoka Univ. |
Object Tracking by a Combination of Discrete DP and Analytical DP Hiroki Kawano, Ikko Fujimura, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) PRMU2010-78 IBISML2010-50 |
Visual object tracking by popular dynamic programming (DP) requires huge computations, although it can provide stable tr... [more] |
PRMU2010-78 IBISML2010-50 pp.165-171 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 10:00 |
Fukuoka |
Fukuoka Univ. |
Consistent Localization of Persons by Integrating Global and Local Observations Yuuki Chijiwa, Yaokai Feng, Seiichi Uchida (Kyushu Univ.) PRMU2010-79 IBISML2010-51 |
We propose a technique for identifying the positions of multiple persons by integrating global observation from an envir... [more] |
PRMU2010-79 IBISML2010-51 pp.173-178 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 10:40 |
Fukuoka |
Fukuoka Univ. |
Minimum Classification Error Training with Automatic Control of Loss Smoothness Junichi Tokuno (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.) PRMU2010-80 IBISML2010-52 |
The smoothness embedded in the Minimum Classification Error formalization has an effect of increasing virtual training s... [more] |
PRMU2010-80 IBISML2010-52 pp.179-184 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 11:10 |
Fukuoka |
Fukuoka Univ. |
Learning Vector Quantization Using a Heavy-tailed Distribution Ansatz Hiroyoshi Miyano, Eiki Ishidera (NEC Informatec Systems) PRMU2010-81 IBISML2010-53 |
This paper presents a novel Lerning Vector Quantization (LVQ) algorithm using a heavy-tailed distribution ansatz. LVQ is... [more] |
PRMU2010-81 IBISML2010-53 pp.185-192 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 11:40 |
Fukuoka |
Fukuoka Univ. |
Evaluation of the error rate of the classifier under the margin assumption Takanori Ayano, Joe Suzuki (Osaka Univ) PRMU2010-82 IBISML2010-54 |
In statistical learning, it is very important for evaluation of the performance of SVM and the conclusion of the difficu... [more] |
PRMU2010-82 IBISML2010-54 pp.193-199 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 10:40 |
Fukuoka |
Fukuoka Univ. |
Action planning for interactive visual scene understanding based on knowledge confidence defined on latent spaces Gurbachan Sekhon (Univ. of British Columbia), Akisato Kimura, Yasuhiro Minami, Hitoshi Sakano, Eisaku Maeda (NTT) PRMU2010-83 IBISML2010-55 |
This report proposes a method for action planning in a system of interactive visual scene understanding through the use ... [more] |
PRMU2010-83 IBISML2010-55 pp.201-208 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 13:40 |
Fukuoka |
Fukuoka Univ. |
[Fellow Memorial Lecture]
- Takio Kurita (Hiroshima Univ.) PRMU2010-84 IBISML2010-56 |
Linear Discriminant Analysis (LDA) is one of the well known methods to extract good features for classification. Otsu de... [more] |
PRMU2010-84 IBISML2010-56 pp.209-214 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 14:50 |
Fukuoka |
Fukuoka Univ. |
[Fellow Memorial Lecture]
From the Subspace Method to the Mutual Subspace Method Ken-ichi Maeda (Toshiba Research/Toshiba) PRMU2010-85 IBISML2010-57 |
The \textit{Subspace Method}~\cite{watanabe2,oja} is a classic method
of pattern recognition, and has been applied to ... [more] |
PRMU2010-85 IBISML2010-57 pp.215-220 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 16:00 |
Fukuoka |
Fukuoka Univ. |
q-normal distribution and its escort distribution
-- What is an escort distribution? -- Masaru Tanaka (Fukuoka Univ.) PRMU2010-86 IBISML2010-58 |
Tsallis entropy, which is one of nonextensive entropies, gives a $q$-normal distribution as an equilibrium probability d... [more] |
PRMU2010-86 IBISML2010-58 pp.237-244 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-06 16:30 |
Fukuoka |
Fukuoka Univ. |
General Scheme of Continuous Dynamic Programming
-- Optimal Full Pixel Matching for Spotting Image -- Ryuichi Oka, Yuichi Yaguchi, Shinya Nizoe (Aizu Univ) PRMU2010-87 IBISML2010-59 |
Two-dimensional Continuous Dynamic Programming (2DCDP) for optimal full pixel matching is discussed. There is a family o... [more] |
PRMU2010-87 IBISML2010-59 pp.245-252 |