Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM |
2020-03-17 10:45 |
Kyoto |
(Cancelled but technical report was issued) |
Semi-Supervised Temporal Segmentation of Industrial Operation Video based on Deep Metric Learning Daiki Kawamori, Kazuaki Nakamura, Naoko Nitta, Noboru Babaguchi (Osaka Univ.) PRMU2019-92 |
Today, cameras are often installed in many production sites for various purposes.
However, untrimmed raw videos captur... [more] |
PRMU2019-92 pp.139-144 |
PRMU, BioX |
2016-03-24 10:00 |
Tokyo |
|
Temporal Spotting of Human Actions in Video Based on Voting Framework with a Hierarchical Action Model Keita Hara, Kazuaki Nakamura, Noboru Babaguchi (Osaka Univ.) BioX2015-42 PRMU2015-165 |
This paper focuses on the task of temporal action spotting: temporal segmentation and classification of human actions in... [more] |
BioX2015-42 PRMU2015-165 pp.7-12 |
IE, ITS, ITE-AIT, ITE-HI, ITE-ME, ITE-MMS, ITE-CE [detail] |
2015-02-24 10:00 |
Hokkaido |
Hokkaido Univ. |
Blind PSNR Estimation of H.264/AVC Compressed Video using Spatio-Temporal Segmentation Masahiro Wakabayashi, Jiro Katto (Waseda Univ.), Naofumi Wada (Samsung) ITS2014-47 IE2014-74 |
In video coding, image quality degradation is inevitable due to quantization steps in the encoding process. We had propo... [more] |
ITS2014-47 IE2014-74 pp.119-124 |
PRMU, CNR |
2014-02-14 15:40 |
Fukuoka |
|
Temporal Spotting of Human Actions from Videos Including Motions Unrelated to Actor's Intention Keita Hara, Kazuaki Nakamura, Noboru Babaguchi (Osaka Univ.) PRMU2013-165 CNR2013-73 |
This paper proposes a method for temporal action spotting: the temporal segmentation and classification of human actions... [more] |
PRMU2013-165 CNR2013-73 pp.183-188 |
NC, MBE (Joint) |
2009-03-12 14:50 |
Tokyo |
Tamagawa Univ. |
Role of statistical learning in grammar-like rule acquisition from speech streams Osamu Watanabe, Miki Hayasaka (Muroran Inst. of Tech.) NC2008-134 |
When infants are acquiring their mother tongues, they have to segment continuous speech streams at first and then discov... [more] |
NC2008-134 pp.183-188 |
SP |
2007-06-28 15:15 |
Fukushima |
The University of Aizu |
Detection of acoustic event boundaries from continuous speech based on constrained clustering Naoya Shimomura, Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2007-12 |
Speech databases with accurate phoneme labeling are often required to improve speech technologies. Although HMM-based fo... [more] |
SP2007-12 pp.25-30 |
MI |
2007-01-27 11:25 |
Overseas |
the Cheju National Univ. |
Volume Analysis of left ventricle and peripheral regions from the temporal series of 3D MR Images Yoshiki Kobayashi, Shinobu Mizuta, Tetsuya Matsuda (Kyoto Univ.) |
It is valuable to examine temporal series of cardiac images for motion analysis of heart. The goal of our research is th... [more] |
MI2006-167 pp.37-40 |
ITS, IPSJ-ITS, IEE-ITS |
2006-09-29 11:30 |
Hokkaido |
Future University Hakodate |
Heirarchy of Algorithm for Image Understanding
-- Collaboration between S-T MRF model and Pattern Recognition algorithms -- Shunsuke Kamijo (IIS, Univ. of Tokyo) |
Spatio-Temporal MRF model segments the spatio-temporal images by refering to the distribution of motion vectors, intensi... [more] |
ITS2006-28 pp.15-21 |
MI |
2006-01-28 13:00 |
Okinawa |
Miyakojimashi-Chuo-Kouminkan |
Visualization of the transition of three-dimensional structure by using Contour Nest Shinobu Mizuta, Yoichi Nakamura, Toshiki Ono, Tetsuya Matsuda (Kyoto Univ.) |
It is a valuable procedure for motion analysis of heart or the analysis of the transition of diseases to analyze tempora... [more] |
MI2005-128 pp.81-84 |