| Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
| IST |
2025-09-18
15:50 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Optimization of Lightweight CNNs Using Feature Images for Edge Devices
Yu Osuka, Ryoya Iegaki, Kota Yoshida, Shunsuke Okura (Ristumeikan Univ.) |
This study investigates lightweight CNN design toward the realization of a feature-extractable CMOS image sensor. First,... [more] |
IST2025-45
pp.37-40 |
| IST, ME, IEICE-IE, IEICE-BioX, IEICE-SIP, IEICE-MI [detail] |
2025-06-05
13:25 |
Ishikawa |
|
A Study of Object Detection Model Compression Methods for Features Extractable CMOS Image Sensors
Ryoya Iegaki, Keiichiro Kuroda, Yu Osuka (Ritsumeikan Univ), Ryuichi Ujiie, Hideki Shima (Nisshinbo), Kota Yoshida, Shunsuke Okura (Ritsumeikan Univ) |
We examine the quantization and pruning of object detection models for CMOS image sensors capable of feature extraction.... [more] |
IST2025-24 ME2025-62
pp.13-17 |
| IST |
2025-03-21
10:45 |
Tokyo |
Kikai-Shinko-Kaikan Bldg.
(Primary: On-site, Secondary: Online) |
Defense Method Against Adversarial Example Attacks using Thermal Noise of a CMOS Image Sensor
Yuki Rogi, Kota Yoshida, Tatsuya Oyama, Takeshi Fujino, Shunsuke Okura (Ritsumeikan Univ.) |
With the rise of IoT technology, edge AI has become increasingly important, but it is vulnerable to adversarial example ... [more] |
IST2025-10
pp.5-6 |
| IEICE-HIP, HI, VRPSY [detail] |
2025-02-19
13:30 |
Ehime |
UNIVERSITY OF HUMAN ENVIRONMENTS |
hight and width estimation of raw images without header
Masaki Emoto (ous) |
Image files such as .jpg, .tiff include image parameters (e.g., width, hight) in their file header. The header is read f... [more] |
HI2025-1
pp.1-2 |
| IEICE-SIS, BCT |
2024-10-04
14:40 |
Hokkaido |
Hokusei Gakuen Univ.
(Primary: On-site, Secondary: Online) |
A Proposal of Labeling-and-DUDE-based Denoising Method for Binary Image
Masato Tada, Ayaka Fujita, Noriaki Suetake (Yamaguchi Univ.) |
Since the loss of information due to noise in binary images is larger than that of grayscale or color images, accurate d... [more] |
|
| HI |
2024-03-19
13:10 |
Online |
|
A Study on Image Selection for Graduation Albums Based on a Large-scale Pre-trained Model and Face Detection
Hiraku Matsuda, Yuta Muraki (OIT), Kazuyuki Fukuda, Kentaro Wada (DAICOLO CO.,LTD.), Mutsuo Sano (OIT) |
When creating a graduation album, there is the task of selecting images to be placed in the layout from among many image... [more] |
HI2024-21
pp.35-38 |
| AIT, IIEEJ, AS, CG-ARTS |
2024-03-05
15:16 |
Tokyo |
Tokyo University of Technology |
A Fundamental Study on 3D CG Image Quality Assessment in Vision & Language Based on Stable Diffusion
Norifumi Kawabata (Kanazawa Gakuin Univ.) |
GPT-4, which is a multimodal large-scale language model, was released on March 14, 2023. GPT-4 is equipped with Transfor... [more] |
AIT2024-115
pp.288-291 |
| ME |
2024-02-10
14:15 |
Online |
online |
Preliminary study on extraction of c-Fos regions from mouse brain images by use of multi-channelization, 1x1 convolution and U-net
Ziyue Wang, Hibiki Okamura, Yu Hayashi, Hotaka Takizawa (Univ. of Tsukuba) |
This report proposes a method for extracting the expression regions of c-Fos protein from brain slice images of experime... [more] |
ME2024-13
pp.44-46 |
| ME, IEICE-EMM, IEICE-IE, IEICE-LOIS, IEE-CMN, IPSJ-AVM [detail] |
2023-09-07
09:50 |
Osaka |
Osaka Metropolitan Univ.
(Primary: On-site, Secondary: Online) |
Improving Performance of Convolutional Neural Network-Based Driver Behavior Recognition
Shengbiao Wang, Koji Iwano (Tokyo City Univ.) |
This study investigates the automatic recognition of driver behaviors using images captured by in-vehicle cameras for th... [more] |
ME2023-90
pp.7-12 |
| IIEEJ, AIT |
2023-06-04
10:40 |
Tokyo |
TOKYO CITY UNIVERSITY
(Primary: On-site, Secondary: Online) |
A Method for Counting Passing People Using Person Detection Based on a Combination of Difference Images and Region Growing
Mirai Amo, Youngha Chang, Nobuhiko Mukai (TCU), Yasuzo Tanaka (Takiguchi Corporation) |
In this study, we propose a method to measure the number of people based on a bird’s-eye movie. Local Binary Patterns (L... [more] |
AIT2023-137
pp.51-54 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-22
14:00 |
Hokkaido |
Hokkaido Univ. |
Hierarchical Minimum-Sized Object Detection Method using Clustering Algorithm for UAV Autonomous Flight
Yusei Horikawa, Makoto Sugaya, Tetsuya Matsumura (Nihon Univ) |
This paper describes an efficient minimum-sized object detection method in high-Resolution images for UAV autonomous fli... [more] |
MMS2023-31 ME2023-51 AIT2023-31
pp.235-238 |
| MMS, ME, AIT, IEICE-IE, IEICE-ITS [detail] |
2023-02-22
13:15 |
Hokkaido |
Hokkaido Univ. |
Semantic-Consistent Style Transfer with Visual Transformers
Jianbo Wang (UTokyo), Huan Yang, Jianlong Fu (MSR), Toshihiko Yamasaki (UTokyo), Baining Guo (MSR) |
Image style transfer has drawn increasing attention recently. This task takes a content image and a style image as input... [more] |
|
| IST |
2022-06-29
13:00 |
Online |
|
Analysis and reduction of thermal noise at multi-conversion gain pixel input
Shoma Harada, Kuo Chiachi, Hayato Horie, Issei Tsukada, Rihito Kuroda (Tohoku Univ.) |
An introduction of multiple conversion gain (MCG) to image sensor is one of the ways to enlarge dynamic range with singl... [more] |
IST2022-25
pp.1-4 |
| IEICE-SIP, IEICE-BioX, IEICE-IE, IEICE-MI, IST, ME [detail] |
2022-05-20
16:20 |
Kumamoto |
Kumamoto University
(Primary: On-site, Secondary: Online) |
Visualization of Important Features for Classifier Decisions using Deep Image Synthesis
Yushi Haku, Megumi Nakao, Tetsuya Matsuda (Kyoto Univ.) |
It is difficult to know the basis for the decisions of machine learning models, and it is necessary to provide a highly ... [more] |
|
| 3DMT |
2022-03-07
14:10 |
Online |
|
Kirameki Display: the current situation of texture representation image/video capturing and generation and next challenges for the future
Naoki Sumi, Keiko Edo, Shuji Hagino (Innolux) |
We have developed “Kirameki display” which is able to represent real texture of materials. And we have also investigated... [more] |
3DIT2022-18
pp.69-72 |
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-22
10:30 |
Online |
online |
A Length Controllable Model for Stylized Image Captioning
Chi Zhang, Li Tao, Yamasaki Toshihiko (UTokyo) |
Stylized image captioning aims at generating captions with styles, based on the input images. In this paper, we aim at g... [more] |
|
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-22
13:00 |
Online |
online |
|
360° cameras have gained popularity over the last few years. Meanwhile, the development of Deep Neural Networks (DNNs) h... [more] |
|
| AIT, ME, MMS, IEICE-IE, IEICE-ITS [detail] |
2022-02-22
13:30 |
Online |
online |
What Kind of Images to Post on Instagram? Image Recommendation for Marketing
Yiwei Zhang, Toshihiko Yamasaki (UTokyo) |
Social media is a popular platform for brands to allocate marketing budget and build their relationship with customers n... [more] |
|
| ME |
2021-12-13
15:20 |
Online |
online |
Automatic Generation of Viewpoint Change Video Using Consistent Regularized Generative Adversarial Networks
Kento Otsu (Ritsumeikan Univ.), Masataka Seo (Osaka Institute of Technology Osaka), Yen-Wei Chen (Ritsumeikan Univ.) |
Gaze plays an important role in conversation. However, in a video call system using a personal computer or the like, it ... [more] |
ME2021-96
pp.33-35 |
| BCT, IEICE-CS, IPSJ-AVM, IEICE-IE [detail] |
2021-11-25
10:50 |
Online |
Online |
Acceleration of Neural Network Visualization RISE by Reduction of Masks
Tomoki Nakada, Imamura Kousuke (Kanazawa Univ.) |
Recently, various techniques have been proposed to visualize the basis for decisions in image recognition using neural n... [more] |
|