Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EMM |
2014-03-07 13:00 |
Ishikawa |
JAIST |
[Invited Talk]
Video Semantic Indexing: Current Trends and Issues Koichi Shinoda (Tokyo Inst. of Tech.) EMM2013-99 |
Recently, many studies have been done for video semantic indexing from a huge amount of consumer video on the Internet. ... [more] |
EMM2013-99 pp.1-2 |
PRMU |
2013-02-22 14:00 |
Osaka |
|
Video Semantic Indexing Using Video-Clip Scores and GMM Supervectors Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) PRMU2012-168 |
We propose a video-semantic-indexing system using video-clip scores and Gaussian-mixture-model (GMM) supervectors. The g... [more] |
PRMU2012-168 pp.173-178 |
PRMU |
2013-02-22 15:00 |
Osaka |
|
Multimedia event detection using camera motion cancelled features and GMM supervectors Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) PRMU2012-170 |
The number of studies for event detection from Internet videos has been increasing. Here, an event is defined as a combi... [more] |
PRMU2012-170 pp.185-190 |
PRMU, IBISML, IPSJ-CVIM (Joint) [detail] |
2012-09-02 10:30 |
Tokyo |
|
q-Gaussian Mixture Models for Video Semantic Indexing Nakamasa Inoue, Koichi Shinoda (Tokyo Inst. of Tech.) PRMU2012-34 IBISML2012-17 |
Gaussian mixture models (GMMs) which extend the bag-of-visual-words (BoW) to a probabilistic framework have been proved ... [more] |
PRMU2012-34 IBISML2012-17 pp.31-36 |
PRMU, SP |
2012-02-10 10:00 |
Miyagi |
|
Large Vocabrary Sign Language Recognition Based on Cheremes Arata Sato, Koichi Shinoda (TokyoTech) PRMU2011-222 SP2011-137 |
We propose a large vocabulary sign language recognition method. While most conventional methods used word units for sign... [more] |
PRMU2011-222 SP2011-137 pp.155-160 |
PRMU, SP |
2012-02-10 14:50 |
Miyagi |
|
Event detection from Video using GMM-Supervectors and SVMs Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda (Tokyo Tech), Shunsuke Sato (Canon) PRMU2011-230 SP2011-145 |
In multimedia event detection, complex target events are detected from a large set of consumer domain videos taken in un... [more] |
PRMU2011-230 SP2011-145 pp.195-200 |
PRMU, SP |
2012-02-10 15:50 |
Miyagi |
|
Two-pass Approach for Recognizing Code-Switching Speech Yonatan Andy Fajar Nugraha, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.), Koji Iwano (Tokyo City Univ.) PRMU2011-235 SP2011-150 |
We propose a recognition method for code-switching utterances in multilingual speech recognition. Code-switching is the ... [more] |
PRMU2011-235 SP2011-150 pp.225-229 |
PRMU, MVE, CQ, IPSJ-CVIM [detail] |
2012-01-20 10:40 |
Osaka |
|
Behavioral event detection from crowds using fixed surveillance cameras Toshiya Wada, Koichi Shinoda (Tokyo Tech) PRMU2011-173 MVE2011-82 |
We propose a method to detect an individual behavioral event in crowds from surveillance video taken by cameras with fix... [more] |
PRMU2011-173 MVE2011-82 pp.257-262 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 10:30 |
Tokyo |
|
Speaker Verification Using MMAP Adaptation Sangeeta Biswas, Johan Rohdin, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.) NLC2011-48 SP2011-93 |
This paper proposes maximum a posteriori (MAP) adaptation of Gaussian mixture models (GMM) using multiple priors for tex... [more] |
NLC2011-48 SP2011-93 pp.133-137 |
PRMU, FM |
2011-12-16 13:00 |
Shizuoka |
Hamamatsu Campus, Shizuoka Univ. |
[Special Talk]
Toward High-Performance Video Semantic Indexing Nakamasa Inoue, Koichi Shinoda (Tokyo Tech) PRMU2011-140 |
TokyoTech, in collaboration with Canon Inc., achieved the best performance in the Semantic Indexing task of TRECVID2011 ... [more] |
PRMU2011-140 pp.89-94 |
SP |
2011-07-23 09:30 |
Hokkaido |
Jozankei Grand Hotel |
Nonlinear Normalization Using q-Logarithm for Robust Speech Recognition Hilman F. Pardede, Koichi Shinoda (Tokyo Inst. of Tech.), Koji Iwano (Tokyo City Univ.) SP2011-49 |
The performance of speech recognition degrades signicantly in the noisy environment. Most compensation methods to improv... [more] |
SP2011-49 pp.45-50 |
SP |
2011-03-05 10:30 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
Analysis of spectral space reduction in noisy speech and its application to noise robust speech recognition Mayumi Beppu, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech) SP2010-122 |
It is widely known that the spectral space of spontaneous speech is
reduced from that
of read speech. This spectral re... [more] |
SP2010-122 pp.43-48 |
PRMU |
2011-02-17 13:00 |
Saitama |
|
[Special Talk]
An overview of video analysis and retrieval evaluation workshop TRECVID2010 Shin'ichi Satoh (NII), Koichi Shinoda (TITECH) PRMU2010-211 |
[more] |
PRMU2010-211 pp.19-24 |
PRMU |
2011-02-17 13:50 |
Saitama |
|
A Multi-modal, Multi-frame Approach for Semantic Indexing in TRECVID Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda (Tokyo Tech) PRMU2010-212 |
We propose a multi-modal, multi-frame approach for semantic indexing in the TRECVID 2010 workshop. The goal of the seman... [more] |
PRMU2010-212 pp.25-30 |
IBISML, PRMU, IPSJ-CVIM [detail] |
2010-09-05 09:30 |
Fukuoka |
Fukuoka Univ. |
Multiple Kernel Learning for Generic Object Recognition Using SIFT Gaussian Mixture Models Nakamasa Inoue, Yusuke Kamishima, Koichi Shinoda, Sadaoki Furui (Tokyo Tech) PRMU2010-58 IBISML2010-30 |
We propose a statistical framework for generic object recognition using SIFT Gaussian mixture models (GMMs) and multiple... [more] |
PRMU2010-58 IBISML2010-30 pp.7-12 |
SP, EA, SIP |
2010-05-26 13:25 |
Hyogo |
Konan Univ. (Hirao Seminar House) |
Online Speech Separation based on Spectral Subtraction for Meeting Speech Recognition Yu Nasu, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.) EA2010-2 SIP2010-2 SP2010-2 |
This paper proposes a speech separation method for meeting speech recognition, which operates in real time. The proposed... [more] |
EA2010-2 SIP2010-2 SP2010-2 pp.7-12 |
PRMU, IE, MI |
2010-05-14 15:30 |
Aichi |
Chubu Univ. |
Surveillance Event Detection Using Local and Global Features Yusuke Yoshizawa (TokyoTech), Koichi Shinoda, Sadaoki Furui (titech) IE2010-43 PRMU2010-31 MI2010-31 |
[more] |
IE2010-43 PRMU2010-31 MI2010-31 pp.163-168 |
PRMU |
2009-11-27 09:00 |
Ishikawa |
Ishikawa Industrial Promotion Center |
High-level Feature Extraction from Video Using SIFT GMM and Acoustic Features Nakamasa Inoue, Tatsuhiko Saito, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech) PRMU2009-106 |
We propose a statistical framework for high-level feature (HLF) extraction, which employs SIFT Gaussian Mixture Models (... [more] |
PRMU2009-106 pp.97-102 |
PRMU |
2009-02-20 09:00 |
Tokyo |
Univ. of Tokyo (IIS) |
Gait Recognition Using CHLAC Features and Hidden Markov Models Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.) PRMU2008-224 |
Variations in speed have a strong impact on gait recognition performance. In this paper, we propose a gait recognition m... [more] |
PRMU2008-224 pp.99-102 |
PRMU |
2009-02-20 11:15 |
Tokyo |
Univ. of Tokyo (IIS) |
Automatically Estimating Number of Scenes for Video Summarization using Model Selection Criteria Koji Yamasaki, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.) PRMU2008-231 |
This paper describes a video summarization system using model selection techniques to estimate the optimal number of sce... [more] |
PRMU2008-231 pp.139-144 |