Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IE, MVE, CQ, IMQ (Joint) [detail] |
2024-03-15 15:30 |
Okinawa |
Okinawa Sangyo Shien Center (Primary: On-site, Secondary: Online) |
High Precision Anomaly Detection using PaDiM based on Pre-training with Normality Constraint of Normal Features Hiroki Kobayashi, Manabu Hashimoto (Chukyo Univ.) IMQ2023-89 IE2023-144 MVE2023-118 |
In recent years, automatic visual inspection is expected with machine learning. Among them, PaDiM is attracting attentio... [more] |
IMQ2023-89 IE2023-144 MVE2023-118 pp.408-413 |
SS |
2024-03-07 17:45 |
Okinawa |
(Primary: On-site, Secondary: Online) |
For evaluating the effectiveness of CodeT5 transfer learning in refactoring recommendations. Yuto Nakajima, Kenji Fujiwara (Tokyo City University) SS2023-62 |
Refactoring is "the process of restructuring the internal architecture of software to make it easier to understand and m... [more] |
SS2023-62 pp.79-84 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 15:45 |
Okinawa |
(Primary: On-site, Secondary: Online) |
|
We have developed automatic speech recognition and dialect identification techniques by using COJADS, a corpus of Japane... [more] |
|
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 16:35 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Large Scale Pre-training and Dynamic Convolution for Image Restoration Under Bad Weather Conditions Shugo Yamashita, Masaaki Ikehara (Keio Univ.) EA2023-128 SIP2023-175 SP2023-110 |
We propose a convolution-based Encoder-Decoder model for removing degradation caused by multiple weather conditions such... [more] |
EA2023-128 SIP2023-175 SP2023-110 pp.394-399 |
NC, MBE, NLP, MICT (Joint) [detail] |
2024-01-24 14:00 |
Tokushima |
Naruto University of Education |
Exploration of Soft Palate Image Based Diagnostic System for High-Risk Individuals of Esophageal Cancer Keishi Okubo, Masato Kiyama, Motoki Amagasaki, Kotaro Waki, Katsuya Nagaoka, Yasuhito Tanaka (Kumamoto Univ.) NC2023-41 |
Previous studies have shown that certain findings of the soft palate are associated with the risk of esophageal squamous... [more] |
NC2023-41 pp.17-22 |
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 09:20 |
Tottori |
(Primary: On-site, Secondary: Online) |
Co-speech Gesture Generation with Variational Auto Encoder Shihichi Ka, Koichi Shinoda (Tokyo Tech) PRMU2023-29 |
Co-speech gesture generation is the study of generating gestures from speech. In prior works, deterministic methods lear... [more] |
PRMU2023-29 pp.74-79 |
MI, MICT |
2023-11-14 15:00 |
Fukuoka |
|
Pre-training without natural images for Cystoscopic AI Diagnosis of Bladder Cancer Ryuunosuke Kounosu (AIST/Toho Univ.), Wonjik Kim (AIST), Atsushi Ikeda (Univ. of Tsukuba), Hirokazu Nosato (AIST), Yuu Nakajima (Toho Univ.) MICT2023-34 MI2023-27 |
When developing AI models, it is sometimes difficult to collect sufficient training data. In these cases, pre-trained AI... [more] |
MICT2023-34 MI2023-27 pp.37-40 |
NLC |
2023-09-06 14:10 |
Osaka |
Osaka Metropolitan University. Nakamozu Campus. (Primary: On-site, Secondary: Online) |
Construction and Validation of Pre-trained Language Model Using Corpus of National and Local Assembly Minutes Keiyu Nagafuchi (HU), Eisaku Sato, Yasutomo Kimura (OUC), Kazuma Kadowaki (JRI), Kenji Araki (HU) NLC2023-3 |
In recent years, there has been a surge in pre-trained language models based on the large-scale corpora derived from the... [more] |
NLC2023-3 pp.12-17 |
EA, ASJ-H, ASJ-MA, ASJ-SP |
2023-07-03 10:45 |
Hokkaido |
|
An Idea about Pretraining in EEG Domain Xianhua Su (Univ. Yamanashi/HDU), Wanzeng Kong, Xuanyu Jin (HDU), Teruki Toya, Kenji Ozawa (Univ. Yamanashi) EA2023-15 |
Given that pre-training in the EEG domain is currently performed using unsupervised training, this approach can currentl... [more] |
EA2023-15 pp.58-63 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-23 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Speech Emotion Recognition based on Emotional Label Sequence Estimation Considering Phoneme Class Attribute Ryotaro Nagase, Takahiro Fukumori, Yoichi Yamashita (Ritsumeikan Univ.) SP2023-9 |
Recently, many researchers have tackled speech emotion recognition (SER), which predicts emotion conveyed by speech. In ... [more] |
SP2023-9 pp.42-47 |
SIS, IPSJ-AVM [detail] |
2023-06-15 11:35 |
Shimane |
NIT, Matsue College (Primary: On-site, Secondary: Online) |
Detection of Calcification Regions from Dental Panoramic Radiograph Based on Semantic Segmentation Using Transformers Taito Murano, Mitsuji Muneyasu, Soh Yoshida, Akira Asano (Kansai Univ.), Keiichi Uchida (Matsumoto Dental Univ. Hospital,) SIS2023-3 |
Calcification regions, considered a sign of atherosclerosis, are sometimes observed in the carotid arteries in dental pa... [more] |
SIS2023-3 pp.13-18 |
NLC, IPSJ-NL |
2023-03-18 11:45 |
Okinawa |
OIST (Primary: On-site, Secondary: Online) |
Detection of Parkinson's disease patients from interview data using pre-trained language models Aiichiro Hayatsu, Ryohei Sasano, Koichi Takeda (Nagoya Univ.) NLC2022-24 |
It is estimated that Parkinson’s disease (PD) affects 150,000 people in Japan, and the number of patients increases as s... [more] |
NLC2022-24 pp.28-31 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 09:20 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Relation Between Shape/Texture Biases and Double-Descent Phenomenon in Visual Recognition Shuya Takahashi (Tokyo Denki Univ./AIST), Nakamasa Inoue, Rio Yokota (Tokyo Tech), Hirokatsu Kataoka (AIST), Eisaku Maeda (Tokyo Denki Univ.) PRMU2022-60 IBISML2022-67 |
Under certain conditions, the learning performance of machine learning undergoes a strange phenomenon called double-desc... [more] |
PRMU2022-60 IBISML2022-67 pp.13-16 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 11:05 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
On the Effectiveness of Formula-Driven Supervised Learning for Medical Image Tasks Ryuto Endo, Shuya Takahashi, Eisaku Maeda (TDU) PRMU2022-71 IBISML2022-78 |
Deep learning for image information processing often uses manually maintained natural image data. However, these data ha... [more] |
PRMU2022-71 IBISML2022-78 pp.71-75 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-02 16:40 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Does the class imbalance in the pre-training always adversely affect transfer learning performance? Shojun Nakayama (Toshiba) PRMU2022-89 IBISML2022-96 |
In this work, we studied how class-imbalance in the pre-training affect to the accuracy of the transfer learning. We div... [more] |
PRMU2022-89 IBISML2022-96 pp.151-156 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2023-02-21 14:45 |
Hokkaido |
Hokkaido Univ. |
A Note on Improvement of Binauralization Performance Based on Multi-view Learning on 360° Videos Masaki Yoshida, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
In this paper, we propose a binaural audio generation method based on multi-view learning using 360◦ videos. Conventiona... [more] |
|
RISING (3rd) |
2022-10-31 10:30 |
Kyoto |
Kyoto Terrsa (Day 1), and Online (Day 2, 3) |
[Poster Presentation]
Making a Pre-training Model of Deep Reinforcement Learning for TCP Congestion Control using Different Communication Environments Takumi Odagawa, Satoshi Ohzahata, Ryo Yamamoto (UEC) |
Congestion control is becoming more important as network usage increases. In recent years, congestion controls using Dee... [more] |
|
EA |
2022-05-13 15:00 |
Online |
Online |
Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino (NTT) EA2022-9 |
Many application studies rely on audio DNN models pre-trained on a large-scale dataset as essential feature extractors, ... [more] |
EA2022-9 pp.41-45 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-04 17:10 |
Online |
Online |
A Vocoder-free Any-to-Many Voice Conversion using Pre-trained vq-wav2vec Takeshi Koshizuka, Hidefumi Ohmura, Kouichi Katsurada (TUS) EA2020-89 SIP2020-120 SP2020-54 |
Voice conversion (VC) is a technique that converts speaker-dependent non-linguistic information to another speaker's one... [more] |
EA2020-89 SIP2020-120 SP2020-54 pp.176-181 |
KBSE, SC |
2020-11-13 15:22 |
Online |
Online + Kikai-Shinko-Kaikan Bldg. (Primary: Online, Secondary: On-site) |
[Poster Presentation]
Automation of Ontology Generation by Pre-trained Language Model Atusi Oba, Ayato Kuwana, Paik Incheon (UoA) KBSE2020-22 SC2020-26 |
As an initial attempt of ontology generation with neural network, Recurrent Neural Network (RNN) based method is propose... [more] |
KBSE2020-22 SC2020-26 p.40 |