Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLP |
2024-05-10 10:55 |
Kagawa |
Kagawa Prefecture Social Welfare Center |
Analysis of the role of latent variables in image classification in deep learning models Kenya Jin'no, Mizuki Dai, Haruki Wakasa, Hiroki Tamegai (Tokyo City Univ.) |
(To be available after the conference date) [more] |
|
NLP, MSS |
2024-03-13 10:00 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
A Study on the Relationship Between Language Model Structure and Complexity of Training Data Wataru Nakano, Jinno Kenya (TCU) MSS2023-70 NLP2023-122 |
[more] |
MSS2023-70 NLP2023-122 pp.1-4 |
NLP, MSS |
2024-03-13 16:05 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Effectiveness and Validation of Feature Scaling in Image Classification Tasks Using CNN Hiroki Tamegai, Kenya Jinno (TCU) MSS2023-81 NLP2023-133 |
In image classification tasks, features are extracted using neural networks and learning is performed by calculating the... [more] |
MSS2023-81 NLP2023-133 pp.54-57 |
NLP, MSS |
2024-03-14 10:50 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Fake Image Detection Focused on Local Regions Takumi Owada, Kenya Jinno (Tokyo City Univ.) MSS2023-88 NLP2023-140 |
We Propose a novel method for detection of images generated by Diffusion Models. We also investigate the attention of ou... [more] |
MSS2023-88 NLP2023-140 pp.83-86 |
NLP, MSS |
2024-03-14 15:15 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Zero-shot class separation degree of the feature extractor Chisato Takahashi, Kenya Jin'no (Tokyo City Univ.) MSS2023-95 NLP2023-147 |
Network Architecture Search (NAS) is a method to automatically search for the optimal structure of a neural network. Sin... [more] |
MSS2023-95 NLP2023-147 pp.115-118 |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-25 09:00 |
Tokushima |
Naruto University of Education |
The Relationship Between Metrics in the Latent Variable Space and Image Classification Performance Haruki Wakasa, Kenya Jin'no (Tokyo City Univ.) NLP2023-99 MICT2023-54 MBE2023-45 |
In recent years, models based on convolutional neural networks (CNNs) have exhibited high performance in image classific... [more] |
NLP2023-99 MICT2023-54 MBE2023-45 pp.78-81 |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-25 10:50 |
Tokushima |
Naruto University of Education |
Analysis of CNN Feature Extraction with Emphasis on Frequency Domain Sora Togawa, Kenya Jin'no (Tokyo City Univ.) NLP2023-104 MICT2023-59 MBE2023-50 |
[more] |
NLP2023-104 MICT2023-59 MBE2023-50 pp.98-101 |
NLP |
2023-11-28 10:50 |
Okinawa |
Nago city commerce and industry association |
Investigation of differences in latent variable space for different datasets in Sentence-BERT's image generation model Masato Izumi, Kenya Jin'no (Tokyo City Univ.) NLP2023-61 |
We have verified the degree to which sentence vectors, which are distributed representations of sentences generated by S... [more] |
NLP2023-61 pp.11-14 |
NLP |
2023-11-28 13:50 |
Okinawa |
Nago city commerce and industry association |
Considerations on the distribution of latent variables in CNNs Mizuki Dai, Kenya Jin'no (Tokyo City Univ.) NLP2023-65 |
Abstract Fully comprehending the output decision mechanisms of neural networks is a critical challenge. This article foc... [more] |
NLP2023-65 pp.31-34 |
NLP, CAS |
2023-10-06 16:20 |
Gifu |
Work plaza Gifu |
Investigating the Learning Performance of Hysteresis Reservoir Computing Kenta Yokoyama, Kenya Jin'no (Tokyo City Univ.) CAS2023-46 NLP2023-45 |
Reservoir computing can acquire larger memory capacity and higher expressive power by properly designing the internal st... [more] |
CAS2023-46 NLP2023-45 pp.70-73 |
NLP |
2023-05-13 13:25 |
Fukushima |
Kenshin Koriyama Cultural Center (Koriyama, Fukushima) |
Fundamental Considerations in Representation Learning for Multimodal Processing Kenya Jin'no, Masato Izumi, Saki Okamoto, Tatsuro Inami, Mizuki Dai, Chisato Takahashi (Tokyo City Univ.) NLP2023-6 |
[more] |
NLP2023-6 pp.23-28 |
NLP, MSS |
2023-03-17 13:10 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Periodic Memory and Learning Chaotic Dynamical Systems in Hysteresis Reservoir Computing Tsukasa Saito, Kenya Jin'no (Tokyo City Univ.) MSS2022-100 NLP2022-145 |
Hysteresis Reservoir Computing, which applies a simple hysteresis network to the reservoir layer of reservoir computing,... [more] |
MSS2022-100 NLP2022-145 pp.178-181 |
CCS |
2022-11-18 09:00 |
Mie |
(Primary: On-site, Secondary: Online) |
Voice Quality Conversion by Two-Step Process of Speech Feature Extraction and Speaker-Controlled Speech Synthesis Taichi Fukawa, Kenya Jin'no (Tokyo City Univ.) CCS2022-52 |
Many methods have been proposed in the field of voice quality conversion that use a style-transforming autoencoder. Howe... [more] |
CCS2022-52 pp.47-52 |
CCS |
2022-11-18 09:50 |
Mie |
(Primary: On-site, Secondary: Online) |
Consideration of an indicator of the total channels suitable for CNN Chisato Takahashi, Kenya Jin'no (TCU) CCS2022-54 |
Neural Architecture Search (NAS), which aims to automatically optimize the structure in order to search for neural netwo... [more] |
CCS2022-54 pp.57-60 |
CCS |
2022-11-18 10:55 |
Mie |
(Primary: On-site, Secondary: Online) |
Simulation of herd generation using Boids Yusuke Nakazato, Kenya Jinno (Tokyo City Univ.) CCS2022-56 |
[more] |
CCS2022-56 pp.67-70 |
IN, CCS (Joint) |
2022-08-04 10:20 |
Hokkaido |
Hokkaido University(Centennial Hall) (Primary: On-site, Secondary: Online) |
Consideration of the structure of CNN models with high image classification performanc Mizuki Dai, Kenya Jinno (Tokyo City University) CCS2022-27 |
In recent years, Transformer-based models such as ViT have shown remarkable performance in image recognition using Deep ... [more] |
CCS2022-27 pp.6-9 |
IN, CCS (Joint) |
2022-08-04 11:10 |
Hokkaido |
Hokkaido University(Centennial Hall) (Primary: On-site, Secondary: Online) |
A Study on the Role of Latent Variables in Auto Encoder and U-Net Saki Okamoto, Kenya Jinno (Tokyo City Univ.) CCS2022-29 |
Using U-Net, which introduces Contracting Paths (Concat) into Auto Encoder (AE), we trained the system to output a front... [more] |
CCS2022-29 pp.16-19 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-22 10:30 |
Online |
Online |
On the relationship between properties of the hysteresis reservoir layer and the training output sequence Tsukasa Saito, Kenya Jin'no (Tokyo City Univ) NLP2021-99 MICT2021-74 MBE2021-60 |
Reservoir computing is a type of machine learning model that can be trained at low cost and fast. However, conventional ... [more] |
NLP2021-99 MICT2021-74 MBE2021-60 pp.121-124 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-22 16:00 |
Online |
Online |
Prototype of a Japanese fingerspelling recognition system using MediaPipe and SVM Masanao Yasumuro, Kenya Jin'no (Tokyo City Univ.) NLP2021-115 MICT2021-90 MBE2021-76 |
[more] |
NLP2021-115 MICT2021-90 MBE2021-76 pp.205-208 |
NLP |
2021-12-18 13:25 |
Oita |
J:COM Horuto Hall OITA |
Consideration of a new evaluation criterion based on the Fisher criterion for label estimation of data Ryuhei Motoki, Kenya Jin'no (Tokyo City Univ.) NLP2021-62 |
In supervised learning, training data is labeled. In addition, a large amount of data is required to improve the accurac... [more] |
NLP2021-62 pp.86-89 |