Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM |
2022-05-13 10:45 |
Aichi |
Toyota Technological Institute |
Efficient DNN model for word lip-reading Daiki Arakane, Takeshi Saitoh (Kyutech) PRMU2022-4 |
This paper studies various deep learning models for lip-reading technology, including one of supervised learning of the ... [more] |
PRMU2022-4 pp.18-23 |
WIT, HI-SIGACI |
2021-12-08 15:20 |
Online |
Online |
Report of Japanese lip reading ability test Takeshi Saitoh (Kyutech), Hajime Tachiiri (Ehime Univ.) WIT2021-34 |
In this paper, to measure Japanese lip-reading ability, we created four Japanese lip-reading ability tests of single sou... [more] |
WIT2021-34 pp.13-17 |
SP, WIT, IPSJ-SLP, ASJ-H [detail] |
2021-10-19 10:35 |
Online |
Online |
Development of eyeglass-type switch for ALS patients using eye movement based on pupil center detection Kazuki Sakamoto, Takeshi Saitoh (Kyushu Insti .of Tech.), Kazuyuki Itoh (NRCPD) SP2021-27 WIT2021-20 |
This research develops an eyeglass-type switch which can be connected to a communication device using the eye movement f... [more] |
SP2021-27 WIT2021-20 pp.18-23 |
WIT, SP, IPSJ-SLP [detail] |
2020-10-22 15:50 |
Online |
Online |
3D-CNN-based mouth shape recognition for patient with intractable neurological diseases Yuya Nakamura, Takeshi Saitoh (kyutech), Kazuyuki Itoh (NRCPD) SP2020-13 WIT2020-14 |
[more] |
SP2020-13 WIT2020-14 pp.27-32 |
NLC |
2020-02-17 09:55 |
Tokyo |
Seikei University |
Facilitator Identification Using Multimodal Information in Multi-party Conversation Kouki Honda, Tukasa Shiota, Kazutaka Shimada, Takeshi Saitoh (Kyutech) NLC2019-41 |
Predicting roles of participants in a conversation is one of the most important tasks for conversation understanding. In... [more] |
NLC2019-41 pp.27-32 |
NLC |
2020-02-17 10:20 |
Tokyo |
Seikei University |
Analysing emergency care team leaders' eye gaze for understanding non-verbal behaviours in emergency care interaction Keiko Tsuchiya, Akira Taneichi (YCU), Kyota Nakamura (YCU Medical Cetnre), Takuma Sakai (YKH), Takeru Abe (YCU Medical Cetnre), Takeshi Saitoh (Kyutech) NLC2019-42 |
In emergency care interaction, a team leader collaborates with his members to safely perform medical procedures. This pr... [more] |
NLC2019-42 pp.33-36 |
WIT, SP |
2019-10-27 10:50 |
Kagoshima |
Daiichi Institute of Technology |
Mouth shape recognition for patient with intractable neurological diseases Yuya Nakamura, Takeshi Saitoh (Kyutech), Kazuyuki Itoh (NRCPD) SP2019-33 WIT2019-32 |
Patients with intractable neuropathy may use a mouth-shape character-based communication as an alternative to communicat... [more] |
SP2019-33 WIT2019-32 pp.93-98 |
WIT, SP |
2018-10-28 09:50 |
Fukuoka |
Kyushu Institute of Technology(Kitakyushu) |
Experimental report on elderly speech disorder person for new substitute speech using lip reading Takeshi Saitoh, Michiko Kubokawa (kyutech), Misato Hirai, Yasuyuki Noyama (Okayama saiseikai General Hospital) SP2018-42 WIT2018-30 |
Writing and sign language are known as substitute methods of verbal communication. The laryngectomized person uses three... [more] |
SP2018-42 WIT2018-30 pp.51-55 |
PRMU, BioX |
2018-03-19 10:50 |
Tokyo |
|
SSSD: Japanese Speech Scene Database by Smart Device for Visual Speech Recognition Takeshi Saitoh, Michiko Kubokawa (Kyushu Inst. of Tech.) BioX2017-63 PRMU2017-199 |
Speech scenes of conventional database available for lip reading or visual speech recognition (VSR), were record with a ... [more] |
BioX2017-63 PRMU2017-199 pp.163-168 |
WIT, SP |
2017-10-20 09:30 |
Fukuoka |
Tobata Library of Kyutech (Kitakyushu) |
[Invited Talk]
Research Trends in Silent Speech Recognition
-- Focusing on Lip Reading -- Takeshi Saitoh (Kyutech) SP2017-48 WIT2017-44 |
Silent speech recognition is a technique for understanding speech content without using audio information. There are var... [more] |
SP2017-48 WIT2017-44 pp.77-81 |
WIT, SP |
2017-10-20 10:20 |
Fukuoka |
Tobata Library of Kyutech (Kitakyushu) |
Effective skeletons for sign language recognition Tomoya Kodama, Takeshi Saitoh (Kyutech) SP2017-49 WIT2017-45 |
With the reasonable motion sensor Microsoft Kinect was marketed, a lot of sign language recognition methods using Kinect... [more] |
SP2017-49 WIT2017-45 pp.83-87 |
WIT |
2016-10-16 14:55 |
Saga |
Karatsu Royal Hotel (Saga pref.) |
Sign language recognition by convolutional neural network with concatenated sequence image of depth image Keisuke Hashimura, Takeshi Saitoh (kyutech) WIT2016-36 |
We proposed a concatenated frame image (CFI) that some sampled frame images from the scene are concatenated like a two-d... [more] |
WIT2016-36 pp.17-22 |
PRMU, CNR |
2016-02-21 09:30 |
Fukuoka |
|
Fish Image Recognition using Convolutional Neural Network Kentaro Wakisaka, Takeshi Saitoh (kyutech) PRMU2015-132 CNR2015-33 |
We are studying on development of image-based fish identification system. Most traditional researches use the geometric ... [more] |
PRMU2015-132 CNR2015-33 pp.1-5 |
PRMU, CNR |
2016-02-22 11:30 |
Fukuoka |
|
[Poster Presentation]
Study on Facial Feature Point Detection using Constrained Local Model Kenta Hara, Takeshi Saitoh (kyutech) PRMU2015-154 CNR2015-55 |
(To be available after the conference date) [more] |
PRMU2015-154 CNR2015-55 pp.121-122 |
PRMU, CNR |
2016-02-22 11:30 |
Fukuoka |
|
[Poster Presentation]
Gaze analysis on reading sign language scene Takanori Sukemune, Masataka Shibuya, Kenji Kawada, Takeshi Saitoh (kyutech) PRMU2015-158 CNR2015-59 |
(To be available after the conference date) [more] |
PRMU2015-158 CNR2015-59 pp.129-130 |
PRMU, CNR |
2016-02-22 16:30 |
Fukuoka |
|
Eye Detection by using Gradient Value for Improvement Performance of Wearable Gaze Estimation System Chinsatit Warapon, Takeshi Saitoh (Kyutech) PRMU2015-163 CNR2015-64 |
This paper presents a fast and precious eye detection technique by using gradient value for improve the performance of w... [more] |
PRMU2015-163 CNR2015-64 pp.149-154 |
WIT, SP, ASJ-H, PRMU |
2015-06-19 10:50 |
Niigata |
|
Feature Points-based Model-Free Object Trajectory Detection Hiroki Nishino, Takeshi Saitoh (kyutech) PRMU2015-55 SP2015-24 WIT2015-24 |
This paper proposes a feature points-based model-free object trajectory detection method. In our method, first, feature... [more] |
PRMU2015-55 SP2015-24 WIT2015-24 pp.137-142 |
WIT, SP, ASJ-H, PRMU |
2015-06-19 11:15 |
Niigata |
|
Text input system using mouth shape pattern and vowel-based word Maki Iinuma, Takeshi Saitoh (Kyutech) PRMU2015-56 SP2015-25 WIT2015-25 |
[more] |
PRMU2015-56 SP2015-25 WIT2015-25 pp.143-148 |
MBE |
2015-01-23 14:50 |
Kumamoto |
Kumamoto University |
Efficient Features for Sign Language Word Recognition using Kinect Tomoki Koyama, Takeshi Saitoh (Kyutech) MBE2014-115 |
The aim of our research is a development of the sign language recognition system for smooth communication between hearin... [more] |
MBE2014-115 pp.117-120 |
EMM |
2014-05-16 11:15 |
Tokyo |
|
[Tutorial Lecture]
Lip reading Takeshi Saitoh (Kyutech) EMM2014-6 |
Lip reading is a technique of understanding speech content by visually acquiring the movements of the lips. This technol... [more] |
EMM2014-6 pp.29-34 |