Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM |
2024-05-16 15:10 |
Tokyo |
(Primary: On-site, Secondary: Online) |
A Proposal for Generating Incorrect Pairs for the CLIP Learning based on Image Clustering Rina Tagami, Hiroki Kobayashi, Shuichi Akizuki, Manabu Hashimoto (Chukyo Univ.) |
(To be available after the conference date) [more] |
|
MI |
2024-03-03 16:54 |
Okinawa |
OKINAWAKEN SEINENKAIKAN (Primary: On-site, Secondary: Online) |
Domain generalization with WSI feature Yuki Shigeyasu (Kyushu Univ.), Shota Harada (Hiroshima City Univ.), Mariyo Kurata, Kazuhiro Terada, Naoki Nakazima (Kyoto Univ.), Akihiko Yoshizawa (Nara Medical Univ.), Hiroyuki Abe, Tetsuo Ushiku (Tokyo Univ.), Ryoma Bise (Kyushu Univ.) MI2023-58 |
In this study, we propose a domain generalization method for pathological images (WSI). Domain shifts in pathological im... [more] |
MI2023-58 pp.81-84 |
PRMU, MVE, VRSJ-SIG-MR, IPSJ-CVIM |
2024-01-25 10:03 |
Kanagawa |
Keio Univ. (Hiyoshi Campus) |
Estimation of 3D Coordinates of Fingertips using Contrastive Embeddings from Hand Images Tatsuya Abe, Takeshi Umezawa, Noritaka Osawa (Chiba Univ.) PRMU2023-40 |
This study evaluated a method for estimating the 3D coordinates of fingertips from hand images when manipulating objects... [more] |
PRMU2023-40 pp.7-12 |
IBISML |
2023-09-08 13:25 |
Osaka |
Osaka Metropolitan University (Nakamozu Campus) (Primary: On-site, Secondary: Online) |
Consideration of Negative Samples in Contrastive Learning Daiki Ishiguro, Tomoko Ozeki (Tokai Univ.) IBISML2023-28 |
Contrastive learning has achieved accuracy comparable to supervised learning. In this method, the transformed image pair... [more] |
IBISML2023-28 pp.16-21 |
NLC, IPSJ-NL |
2023-03-18 16:20 |
Okinawa |
OIST (Primary: On-site, Secondary: Online) |
Contrastive Learning with Attention Pooling for Long Document Summarization Tsukasa Kamo, Toru Sugimoto (SIT) NLC2022-28 |
Automatic summarization using neural networks has improved with the advent of pre-training models based on the Transform... [more] |
NLC2022-28 pp.50-54 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-02-28 15:55 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Self-Supervised Learning With Spatial Audio-Visual Recording for Sound Event Localization and Detection Yoto Fujita (Kyoto Univ.), Yoshiaki Bando (AIST), Keisuke Imoto (Doshisha Univ./AIST), Masaki Onihsi (AIST), Yoshii Kazuyoshi (Kyoto Univ.) EA2022-89 SIP2022-133 SP2022-53 |
This paper describes an unsupervised pre-training method for sound event localization and detection (SELD) on multi-chan... [more] |
EA2022-89 SIP2022-133 SP2022-53 pp.78-82 |
IBISML |
2022-12-22 15:30 |
Kyoto |
Kyoto University (Primary: On-site, Secondary: Online) |
[Short Paper]
Semi supervised image classification using unreliable pseudo label Jihong Hu, Yinhao Li, Yen-Wei Chen (Ritsumeikan Univ.) IBISML2022-47 |
Semi-supervised learning (SSL), which automatically annotates unlabeled data with pseudo labels during training, has ach... [more] |
IBISML2022-47 pp.24-29 |
CAS, MSS, IPSJ-AL [detail] |
2022-11-18 14:05 |
Kochi |
(Primary: On-site, Secondary: Online) |
Unsupervised Representation Learning over Decentralized Federated Learning Haruki Sakurai, Hideya Ochiai, Hiroshi Esaki (Univ. Tokyo) CAS2022-54 MSS2022-37 |
Contrastive Learning is a form of self-supervised learning, a method for learning a general-purpose encoder using a larg... [more] |
CAS2022-54 MSS2022-37 pp.79-82 |
PRMU |
2022-09-15 10:15 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
Image retrieval for animated characters from original works, derivative works and merchandise Shiqi Mao (Ritsumeiken Univ), Longjiao Zhao (Nagoya Univ.), Yu Wang (Hitotsubashi Univ.), Jien Kato (Ritsumeiken Univ) PRMU2022-19 |
Recently, there are many successful models for retrieving animated characters. However, conventional studies have mainly... [more] |
PRMU2022-19 pp.55-60 |
SIP |
2022-08-25 13:21 |
Okinawa |
Nobumoto Ohama Memorial Hall (Ishigaki Island) (Primary: On-site, Secondary: Online) |
Style Feature Extraction by Contrastive Learning and Mutual Information Constraints Suguru Yasutomi, Toshihisa Tanaka (TUAT) SIP2022-52 |
Extracting style features is crucial for analyzing data. This paper proposes a style feature extraction using variationa... [more] |
SIP2022-52 pp.13-18 |
TL |
2022-07-10 10:30 |
Online |
Online |
Formation of language subject by foreign learning:
-- Over the physical activity of pronunciation learning -- Tomiko Yuyama (Tokyo Metoropolitan Univ) TL2022-2 |
(To be available after the conference date) [more] |
TL2022-2 pp.7-12 |
SIP, BioX, IE, MI, ITE-IST, ITE-ME [detail] |
2022-05-19 09:40 |
Kumamoto |
Kumamoto University Kurokami Campus (Primary: On-site, Secondary: Online) |
Variational Autoencoders Conditioned by Contrastive Features as Style-Feature Extractors Suguru Yasutomi, Toshihisa Tanaka (TUAT) SIP2022-3 BioX2022-3 IE2022-3 MI2022-3 |
Extracting style features is crucial for investigating the characteristics of data. This paper proposes a variational au... [more] |
SIP2022-3 BioX2022-3 IE2022-3 MI2022-3 pp.13-18 |
TL |
2022-03-13 16:25 |
Online |
Online |
Consideration of Foreign Language Learning Focused on Linguistic ability
-- Chinese-English Contrastive Pronunciation Relearning for Native Speakers of Japanese -- Tomiko Yuyama, Akinobu Kanda (Tokyo Metoropolitan Univ), Kaoru Fujimoto (Musashino Univ), Maiko Shinozuka (Tokyo Metoropolitan Univ), Noriko Takeda (Former Seikei Univ) TL2021-44 |
Under the sharpening English-Chinese polarization structure, it is required to develop international human resources who... [more] |
TL2021-44 pp.68-73 |
PRMU, IPSJ-CVIM |
2022-03-11 10:45 |
Online |
Online |
Self-supervised Contrastive Learning Using Triplet Loss for Offline Recognition of Handwritten Chinese Text lines Trung Tan Ngo, Hung Tuan Nguyen, Masaki Nakagawa (TUAT) PRMU2021-78 |
In this paper, we propose a framework for contrastive learning of visual representations using online triplet loss and a... [more] |
PRMU2021-78 pp.115-120 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-22 10:00 |
Online |
Online |
Pretext-Contrastive Learning for Self-Supervised Video Feature Learning Li Tao (UTokyo), Xueting Wang (CyberAgent, Inc.), Toshihiko Yamasaki (UTokyo) ITS2021-43 IE2021-52 |
Recently, pretext task-based methods are proposed one after another in self-supervised video feature learning. Contrasti... [more] |
ITS2021-43 IE2021-52 pp.109-114 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-22 10:15 |
Online |
Online |
Contrastive Self-Supervised Learning Framework for Unsupervised Video Summarization Xianliang Zhang, Li Tao (UTokyo), Xueting Wang (CyberAgent AI Lab), Toshihiko Yamasaki (UTokyo) ITS2021-44 IE2021-53 |
The rapid growth of video data aggravates the effort by viewers in exploring informative data. This paper presents a fra... [more] |
ITS2021-44 IE2021-53 pp.115-120 |
MI |
2022-01-26 10:13 |
Online |
Online |
[Short Paper]
Abnormality Detection for Covid-19 Chest CT Images by Dimensionality Reduction Based on Contrastive Learning Hiroki Tobise, Kugler Mauricio, Tatsuya Yokota (NITech), Masahiro Hashimoto (Keio Univ.), Yoshito Otake (NAIST), Toshiaki Akashi (Juntendo Univ.), Akinobu Shimizu (TUAT), Hidekata Hontani (NITech) MI2021-53 |
In this article, we propose a method that detects anomaly regions in chest CT images for the aid of Covid-19 diagnosis. ... [more] |
MI2021-53 pp.41-42 |
TL |
2021-07-04 16:30 |
Online |
Online |
An Attempt of Multilingual Learning Focused on Linguistic Ability
-- Considering Learning Method and System for Chinese-Learners to utilize First Language with Reference to Three Languages of Japanese, English, and Chinese -- Tomiko Yuyama (TMU), Noriko Takeda (FSU), Akinobu Kanda (TMU), Kaoru Fujimoto (MU), Maiko Shinozuka (TMU) TL2021-11 |
(To be available after the conference date) [more] |
TL2021-11 pp.44-49 |
MI |
2021-03-16 09:45 |
Online |
Online |
MI2020-66 |
In this paper, we propose a method for automatically classifying COVID-19 cases from CT images of lung fields. Currently... [more] |
MI2020-66 pp.82-86 |
MVE, IMQ, IE, CQ (Joint) [detail] |
2021-03-01 09:45 |
Online |
Online |
Action Detection Based on Supervised Contrastive Learning Keita Iida, Xueting Wang, Toshihiko Yamasaki (The Univ. of Tokyo) IMQ2020-10 IE2020-50 MVE2020-42 |
We propose a method based on supervised contrastive learning in order to extract better feature for action detection. Ac... [more] |
IMQ2020-10 IE2020-50 MVE2020-42 pp.1-6 |