| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| ME |
2026-02-28
11:00 |
Online |
online |
An Examination of Harvest Decision Based on the Two-Sided Maturity of Pears Using Deep Learning and Its Application to Augmented Reality
Kensuke Miyauchi, Mie Sato (Utsunomiya Univ.) |
Harvest decision of pears depends on the experience of the experts. It is difficult for new farmers to master. There are... [more] |
ME2026-40
pp.9-12 |
| IEICE-IE, IEICE-ITS, MMS, ME, AIT, SIP [detail] |
2026-02-19
10:00 |
Hokkaido |
|
Area Light Source Parameter Estimation for Penumbra Representation in AR
Takuto Yoshida, Hiroki Takahashi (UEC) |
To achieve optical consistency in Augmented Reality (AR), it is necessary to accurately estimate the real-world light so... [more] |
MMS2026-1 ME2026-1 AIT2026-1 SIP2026-1
pp.1-4 |
| IEICE-HIP, HI, VRPSY, ASJ-H [detail] |
2026-02-17
10:20 |
Okinawa |
|
A driver's gaze prediction model employing deep learning mechanisms
Risa Yoshie, Yuhei Ohsawa (Kindai Univ.), Fumika Nakanishi, Minori Yamataka (ARIC, DENSO CORP.), Takeshi Kohama (Kindai Univ.) |
Although driver assistance systems have made remarkable progress in recent years, it has been pointed out that system in... [more] |
HI2026-3
pp.12-17 |
| KANSAI |
2025-11-30
09:45 |
Osaka |
OMU I-site Namba |
A Study on Image-Based Visual Inspection of Senbei (Japanese Rice Crackers)
Shu Goto, Masakazu Morimoto (University of Hyogo) |
This study aims to automate quality control (QC) in senbei manufacturing, proposing a system to inspect “baking color”, ... [more] |
|
| KANSAI |
2025-11-30
10:30 |
Osaka |
OMU I-site Namba |
Extraction of Plasterer's Tacit Knowledge and Automatic Generation of Robotic Arm Motions through Deep Predictive Learning
Keisuke Ota, Ikumi Noborio, Makoto Muramoto, Weiwei Du (KIT) |
In plastering work performed by skilled craftsmen, it is possible to respond flexibly to environmental changes through t... [more] |
|
| KANSAI |
2025-11-30
14:15 |
Osaka |
OMU I-site Namba |
Robust Skeleton-Based Action Recognition through Contrastive Language-Skeleton Feature Alignment
Motohiro Isaka, Yen Wei Chen, Jiaqing Liu (Ritsumeikan Univ) |
Recent years, skeleton-based action recognition has seen increasing application in diverse fields such as surveillance, ... [more] |
|
| IST |
2025-11-21
14:00 |
Tokyo |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
Combining Coded-Aperture, Event Camera, and Deep Learning for Light Field Imaging
Keita Takahashi (Nagoya Univ.) |
The concept of light field is used to describe a field of light-rays created by target objects, and it is typically repr... [more] |
IST2025-47
pp.5-9 |
IEICE-CQ, IEE-CMN, BCT
(Joint) [detail] |
2025-11-06
14:55 |
Niigata |
Tokimate |
Intelligent Training Control for Hierarchical Federated Learning in Dynamic Vehicular Environments
Zhaoyang Du, Celimuge Wu, Yangfei Lin, Jiale Wu (UEC) |
Federated Learning (FL) has emerged as a promising solution for enabling privacy-preserving distributed model training i... [more] |
|
| ME |
2025-10-28
15:00 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
A Study of Scene Graph Generation Based on Image Captioning
Masaya Ikeda, Koichi Ito, Takafumi Aoki (Tohoku Univ.) |
Image captions can be accurately generated by using scene graph representation of images. In contrast, the training data... [more] |
ME2025-92
pp.9-12 |
| SMC |
2025-07-24
16:20 |
Tokyo |
Kikai-Shinko-Kaikan Bldg.
(Primary: On-site, Secondary: Online) |
Full-Parallax High-Definition CGH Created Using Ray-Sampling Plane and Free-Viewpoint Images with NeRF
Tada Kengo, Nishi Hirohito, Matsushima Kyoji (Kansai Univ.) |
The method using the ray-sampling plane (RSP) is one of powerful techniques to create full-parallax high-definition comp... [more] |
|
| SMC |
2025-07-25
10:25 |
Tokyo |
Kikai-Shinko-Kaikan Bldg.
(Primary: On-site, Secondary: Online) |
Deep Learning Models for 3D Interfaces with a Ring-Mounted Camera
Matthew Ichikawa, Saori Takeyama, Masahiro Yamaguchi (Institute of Science Tokyo) |
In this study, we introduce a novel hand‐shape and motion estimation method for 3D interfaces that employs a ring‐shaped... [more] |
|
| IIEEJ, AIT |
2025-06-30
15:50 |
Nagano |
(Primary: On-site, Secondary: Online) |
Slope Change Detection using Multiple Instance Learning and Memory Banks from Remote Surveillance Cameras
Kohei Takashima, Yota Yamamoto, Yukinobu Taniguchi (Tokyo Univ of Science) |
Landslides are serious natural disasters that cause extensive damage to human lives and social infrastructure. Preventin... [more] |
AIT2025-170
pp.11-14 |
| IST, ME, IEICE-IE, IEICE-BioX, IEICE-SIP, IEICE-MI [detail] |
2025-06-05
13:00 |
Ishikawa |
|
A Point Cloud Downsampling Method based on SHAP for 3D Object Classification
Ryota Sugimoto, Kenji Kanai, Jiro Katto (Waseda Univ.) |
In recent years, the increasing density of point cloud data has raised concerns regarding the processing burdens in thre... [more] |
|
| IST, ME, IEICE-IE, IEICE-BioX, IEICE-SIP, IEICE-MI [detail] |
2025-06-05
15:25 |
Ishikawa |
|
Application of the Membership Inference Attacks Using Poisoning to Federated Learning
Tomoya Tsukada, Masahiro Mambo (Kanazawa Univ.) |
Even though it is known that membership inference attack becomes more effective against deep learning by using data pois... [more] |
|
| AIT, IIEEJ, AS, CG-ARTS |
2025-03-10
13:37 |
Tokyo |
Tokyo Polytechnic Univ. (Nakano) |
An Experimental Study on 3D Hair Modeling from Sketches Using Diffusion Curves
Ritsuki Ishiwata (Hosei Univ), Syuhei Sato (Hosei Univ/PCGR) |
In this study, we propose a method for generating 3D hair models from sketches. One approach to 3D modeling from a singl... [more] |
AIT2025-67
pp.102-105 |
| AIT, IIEEJ, AS, CG-ARTS |
2025-03-10
14:25 |
Tokyo |
Tokyo Polytechnic Univ. (Nakano) |
SVBRDF Prediction based on Two-Level Basis from Multiple Input Images
Tomoya Kozuki, Kei Iwasaki (Saitama Univ.) |
This paper proposes a model that predicts Spatially Varying Bidirectional Reflectance Distribution Function (SVBRDF) usi... [more] |
AIT2025-70
pp.114-117 |
| BCT, IEEE-BT |
2025-03-07
13:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
How AI Technology Can Empower Broadcast Media
Toru Imai (NHK) |
Since the term ‘Artificial Intelligence’ was coined 70 years ago, AI technology has developed remarkably. In recent year... [more] |
BCT2025-47
pp.18-21 |
| ME, AIT, MMS, IEICE-IE, IEICE-ITS, SIP [detail] |
2025-02-18
11:25 |
Hokkaido |
Hokkaido Univ. |
Efficient Physics Informed Dynamic Neural Fluid Fields Reconstruction From Sparse Video
Yangcheng Xiang, Yoshinori Dobashi (Hokudai) |
Efficiently inferring the latent physical properties of fluids from sparse 2D videos has long been a challenging problem... [more] |
MMS2025-6 ME2025-6 AIT2025-6 SIP2025-6
pp.29-33 |
| KANSAI |
2024-12-22
09:30 |
Osaka |
Osaka Metropolitan University, I-site Namba |
**
Youhei Ueno, Masataka Seo (Osaka Institute of Technology) |
There are two problems with video generation using deep generative models. The first problem is that objects moving betw... [more] |
|
| HI, VRPSY, JSKE |
2024-11-16
10:00 |
Osaka |
Kindai Univ. |
Deep learning mind-reading model based on gaze information
Nayuta Tada, Takeshi Kohama (Kindai Univ.) |
In this study, intending to establish a mind-reading technique based on gaze information, we developed a model that exte... [more] |
HI2024-47
pp.47-50 |