Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
CAS, CS |
2024-03-15 14:45 |
Okinawa |
|
Exploring Uniform Convergence in Neural Networks and its Implication on Generalization Error Zong Xianzhe, Hiroshi Tamura (CHUO Univ.) CAS2023-135 CS2023-128 |
Uniform Convergence, a well-established framework for evaluating generalization in traditional Machine Learning, frequen... [more] |
CAS2023-135 CS2023-128 pp.134-139 |
IE, MVE, CQ, IMQ (Joint) [detail] |
2024-03-14 15:20 |
Okinawa |
Okinawa Sangyo Shien Center (Primary: On-site, Secondary: Online) |
Efficient regularizer for 4D light field image denoising based on graph-learning Rino Yoshida (TUS), Kazuya Kodama (NII), Gene Cheung (York Univ.), Takayuki Hamamoto (TUS) IMQ2023-56 IE2023-111 MVE2023-85 |
Advanced 3D visual media as promising technology often require 4D light fields composed of dense multi-view images for a... [more] |
IMQ2023-56 IE2023-111 MVE2023-85 pp.235-240 |
MI |
2024-03-03 09:53 |
Okinawa |
OKINAWAKEN SEINENKAIKAN (Primary: On-site, Secondary: Online) |
Deep Learning based Objective Microscopic Agglutination Test Risa Nakano, Yuji Oyamada (Tottori Univ.), Ryo Ozuru (Fukuoka Univ.) MI2023-34 |
This paper aims to achieve objective justification of decision criteria in Microscopic Agglutination Test (MAT), which i... [more] |
MI2023-34 pp.15-18 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 15:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Privacy preserving deep unrolling ISTA method for sparse representation Nichika Yuge, Takayuki Nakachi (Univ. of the Ryukyus.) EA2023-81 SIP2023-128 SP2023-63 |
In recent years, the use of edge and cloud computing has expanded. Along with this, a method called sparse modeling is a... [more] |
EA2023-81 SIP2023-128 SP2023-63 pp.121-126 |
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 |
SS, MSS |
2024-01-17 14:30 |
Ishikawa |
(Primary: On-site, Secondary: Online) |
Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator Ryoma Furuyama, Daiki Kuyoshi, Yamane Satoshi (Kanazawa Univ.) MSS2023-55 SS2023-34 |
Imitation learning is often used in addition to reinforcement learning in environments where reward design is difficult ... [more] |
MSS2023-55 SS2023-34 pp.19-24 |
RISING (3rd) |
2023-10-31 14:00 |
Hokkaido |
Kaderu 2・7 (Sapporo) |
[Poster Presentation]
Development and Evaluation of Location Tracking System for Investigating the Influence of Well-being on Family Members' Staying Time in the Same Room Taiki Egusa (Osaka City Univ.), Yoshihiro Nakaso, Yui Ogawa, Manato Fujimoto, Shingo Ata (Osaka Metropolitan Univ.) |
It is important to understand the time spent in the same room by family members in order to obtain new knowledge that ca... [more] |
|
NLP, MSS |
2023-03-17 16:45 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Enhancement of functionality in Deep Echo State Network by optimizing leak rate Shuichi Inoue, Sou Nobukawa (CIT), Haruhiko Nishimura (UOH), Eiji Watanabe (NIBB), Teijiro Isokawa (UOH) MSS2022-110 NLP2022-155 |
Deep echo state network (Deep-ESN) model consists of multiple reservoir layers, which can respond on layer-specific diff... [more] |
MSS2022-110 NLP2022-155 pp.231-236 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2023-03-03 16:20 |
Hokkaido |
Future University Hakodate (Primary: On-site, Secondary: Online) |
Classifying Cable Tendency with Semantic Segmentation by Utilizing Real and Simulated RGB Data Pei-Chun Chien, Powei Liao, Eiji Fukuzawa, Jun Ohya (Waseda Univ.) PRMU2022-117 IBISML2022-124 |
Cable tendency is the potential shape or characteristic that a cable may possess while being manipulated during automate... [more] |
PRMU2022-117 IBISML2022-124 pp.311-318 |
SIS |
2023-03-03 14:30 |
Chiba |
Chiba Institute of Technology (Primary: On-site, Secondary: Online) |
[Tutorial Lecture]
On Semantic Image Processing with Autoencoder Hiroyuki Tsuji (KAIT) SIS2022-58 |
Variational Auto Encoder (VAE) has a conceptually well-structured latent space and can realize semantic image manipulati... [more] |
SIS2022-58 pp.97-102 |
DC |
2023-02-28 14:25 |
Tokyo |
Kikai-Shinko-Kaikan Bldg (Primary: On-site, Secondary: Online) |
Test Point Selection Method Using Graph Neural Networks and Deep Reinforcement Learning Shaoqi Wei, Kohei Shiotani, Senling Wang, Hiroshi Kai, Yoshinobu Higami, Hiroshi Takahashi (Ehime Univ.) DC2022-87 |
It is well known that selecting the optimal test point to maximize the fault coverage is NP-hard. Conventional heuristic... [more] |
DC2022-87 pp.27-32 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-03-01 17:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
RGB-D Salient Object Detection Using Saliency and Edge Reverse Attention Tomoki Ikeda, Masaaki Ikehara (Keio Univ.) EA2022-127 SIP2022-171 SP2022-91 |
Salient Object Detection is a task to detect visually significant objects in an image. Conventional methods have proble... [more] |
EA2022-127 SIP2022-171 SP2022-91 pp.300-305 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2023-02-21 15:30 |
Hokkaido |
Hokkaido Univ. |
A Study on Adaptation Methods for Universal Deep Image Compression Koki Tsubota, Kiyoharu Aizawa (UTokyo) ITS2022-56 IE2022-73 |
In this study, we tackle universal deep image compression, which aims to compress images in arbitrary domains such as li... [more] |
ITS2022-56 IE2022-73 pp.77-82 |
EMM |
2023-01-26 09:55 |
Miyagi |
Tohoku Univ. (Primary: On-site, Secondary: Online) |
On the Transferability of Adversarial Examples between Isotropic Network and CNN models Miki Tanaka (Tokyo Metropolitan Univ.), Isao Echizen (NII), Hitoshi Kiya (Tokyo Metropolitan Univ.) EMM2022-62 |
Deep neural networks are well known to be vulnerable to adversarial examples (AEs). In addition, AEs generated for a sou... [more] |
EMM2022-62 pp.7-12 |
PRMU |
2022-12-15 10:30 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
Single Image Raindrop Removal Using a Non-local Operator and Feature Maps in the Frequency Domain Shinya Ezumi, Masaaki Ikehara (Keio Univ.) PRMU2022-34 |
High-quality raindrop removal is desired for outdoor image processing systems as well as for acquiring good-looking imag... [more] |
PRMU2022-34 pp.13-18 |
PRMU |
2022-12-16 10:15 |
Toyama |
Toyama International Conference Center (Primary: On-site, Secondary: Online) |
Pose-aware Disentangled Multiscale Transformer for Pose Guided Person Image Generation Kei Shibasaki, Masaaki Ikehara (Keio Univ.) PRMU2022-44 |
Pose Guided Person Image Generation (PGPIG) is the task that transforms the pose of a person image from the source image... [more] |
PRMU2022-44 pp.63-69 |
NS, ICM, CQ, NV (Joint) |
2022-11-24 11:10 |
Fukuoka |
Humanities and Social Sciences Center, Fukuoka Univ. + Online (Primary: On-site, Secondary: Online) |
Deep Learning Side-Channel Attack in Noise Based Countermeasure Simon Shu Takemoto, Yoshiya Ikezaki, Yusuke Nozaki, Masaya Yoshikawa (Meijo Univ.) NS2022-103 |
The IoT requires the implementation of cryptographic techniques to ensure the confidentiality, integrity, and availabili... [more] |
NS2022-103 pp.19-22 |
CAS, SIP, VLD, MSS |
2022-06-16 14:40 |
Aomori |
Hachinohe Institute of Technology (Primary: On-site, Secondary: Online) |
Adversarial Robustness of Secret Key-Based Defenses against AutoAttack Miki Tanaka, April Pyone MaungMaung (Tokyo Metro Univ.), Isao Echizen (NII), Hitoshi Kiya (Tokyo Metro Univ.) CAS2022-7 VLD2022-7 SIP2022-38 MSS2022-7 |
Deep neural network (DNN) models are well-known to easily misclassify prediction results by using input images with smal... [more] |
CAS2022-7 VLD2022-7 SIP2022-38 MSS2022-7 pp.34-39 |
CCS, NLP |
2022-06-09 17:15 |
Osaka |
(Primary: On-site, Secondary: Online) |
Visualization of decisions from CNN models trained on OpenStreetMap images labeled based on traffic accident data Kaito Arase, Zhijian Wu, Tsuyoshi Migita, Norikazu Takahashi (Okayama Univ.) NLP2022-10 CCS2022-10 |
The authors have recently conducted training of Convolutional Neural Networks (CNNs) on OpenStreetMap images each of whi... [more] |
NLP2022-10 CCS2022-10 pp.46-51 |
CCS |
2022-03-27 15:40 |
Hokkaido |
RUSUTSU RESORT HOTEL & CONVENTION (Primary: On-site, Secondary: Online) |
Evaluation of Industrial Anomaly Detection using Diffusion Model Yu Kashihara, Takashi Matsubara (Osaka Univ.) CCS2021-48 |
Anomaly detection by generative models is achieved by comparing the reconstruction and the original image. However, exis... [more] |
CCS2021-48 pp.72-77 |