Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SS, IPSJ-SE, KBSE [detail] |
2022-07-29 13:25 |
Hokkaido |
Hokkaido-Jichiro-Kaikan (Sapporo) (Primary: On-site, Secondary: Online) |
Fault Localization for RNNs Based on Probabilistic Automata and n-grams Yuta Ishimoto, Masanari Kondo, Naoyasu Ubayashi, Yasutaka Kamei (Kyushu Univ.) SS2022-10 KBSE2022-20 |
If deep learning models misbehave, serious accidents may occur.Previous studies have proposed approaches to overcome suc... [more] |
SS2022-10 KBSE2022-20 pp.55-60 |
AP, SANE, SAT (Joint) |
2022-07-27 10:15 |
Hokkaido |
Asahikawa Taisetsu Crystal Hall (Primary: On-site, Secondary: Online) |
[Invited Lecture]
RNN Based Proactive Prediction of Received Power Using Environmental Information Motoharu Sasaki, Naoki Shibuya, Kenichi Kawamura, Nobuaki Kuno, Minoru Inomata, Wataru Yamada, Takatsune Moriyama (NTT) AP2022-36 |
We report a method for predicting received power using a GRU (Gated Recurrent Unit), which is one of the RNNs (Recurrent... [more] |
AP2022-36 pp.12-16 |
EMD, WPT, EMCJ, PEM (Joint) |
2022-07-15 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Prediction of E-field Distribution in Indoor Environments Using Deep Learning Technique Liu Sen, Onishi Teruo, Taki Masao, Watanabe Soichi (NICT) EMCJ2022-34 |
As one of the important aspects of monitoring electromagnetic field (EMF) exposure levels, comprehensively grasping the ... [more] |
EMCJ2022-34 pp.1-5 |
AI |
2022-07-04 10:40 |
Hokkaido |
(Primary: On-site, Secondary: Online) |
Deep Learning Side-Channel Attacks for Rolled Architecture of PRINCE and Midori128 Shu Takemoto, Yoshiya Ikezaki, Yusuke Nozaki, Masaya Yoshikawa (Meijo Univ.) AI2022-3 |
With the recent expansion of small autonomous mobile robots such as drones, cyber security for small devices is very imp... [more] |
AI2022-3 pp.13-18 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-17 15:00 |
Online |
Online |
SP2022-13 |
We investigate the method for unsupervised learning of artifacts correction networks used for post-processing of Multi B... [more] |
SP2022-13 pp.49-54 |
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 |
SIS, IPSJ-AVM |
2022-06-10 13:00 |
Fukuoka |
KIT(Wakamatsu Campus) (Primary: On-site, Secondary: Online) |
[Tutorial Lecture]
How to build a High-Precision and Efficient Robot Vision: Dataset Generation and Hardware Implementation for Deep Learning Hakaru Tamukoh (Kyutech) SIS2022-10 |
This tutorial lecture explains a construction method for high-precision and efficient robot vision that includes a semi-... [more] |
SIS2022-10 pp.45-48 |
SIP, BioX, IE, MI, ITE-IST, ITE-ME [detail] |
2022-05-19 16:10 |
Kumamoto |
Kumamoto University Kurokami Campus (Primary: On-site, Secondary: Online) |
[Invited Talk]
Image and Video Restoration with Deep Learning Satoshi Iizuka (Univ. of Tsukuba) SIP2022-15 BioX2022-15 IE2022-15 MI2022-15 |
In this talk, I will introduce techniques for restoring black-and-white images and videos with high accuracy using deep ... [more] |
SIP2022-15 BioX2022-15 IE2022-15 MI2022-15 p.78 |
SIP, BioX, IE, MI, ITE-IST, ITE-ME [detail] |
2022-05-20 16:40 |
Kumamoto |
Kumamoto University Kurokami Campus (Primary: On-site, Secondary: Online) |
3D Medical Image Segmentation Using 2.5D Deformable Convolutional CNN Yuya Okumura, Kudo Hiroyuki, Takizawa Hotaka (Tsukuba Univ.) SIP2022-29 BioX2022-29 IE2022-29 MI2022-29 |
An effective method to improve the accuracy of 3D medical image segmentation using deep learning is to use deformable co... [more] |
SIP2022-29 BioX2022-29 IE2022-29 MI2022-29 pp.150-155 |
SIP, BioX, IE, MI, ITE-IST, ITE-ME [detail] |
2022-05-20 17:00 |
Kumamoto |
Kumamoto University Kurokami Campus (Primary: On-site, Secondary: Online) |
Deformable registration of 3D medical images with Deep Residual UNet Taiga Nakamura, Yuki Sato, Hiroyuki Kudo, Hotaka Takizawa (Univ. of Tsukuba) SIP2022-30 BioX2022-30 IE2022-30 MI2022-30 |
(To be available after the conference date) [more] |
SIP2022-30 BioX2022-30 IE2022-30 MI2022-30 pp.156-160 |
EA |
2022-05-13 16:50 |
Online |
Online |
Basic study for permutation solver based on deep neural networks Fumiya Hasuike, Rui Watanabe, Daichi Kitamura (NIT, Kagawa) EA2022-13 |
This paper focuses on a permutation problem associated with frequency-domain independent component analysis (FDICA) that... [more] |
EA2022-13 pp.62-67 |
NS |
2022-04-15 11:10 |
Tokyo |
kikai shinkou kaikan + online (Primary: On-site, Secondary: Online) |
Service Chaining Based on Capacitated Shortest Path Tour Problem
-- Solution Based on Deep Reinforcement Learning and Graph Neural Network -- Takanori Hara, Masahiro Sasabe (NAIST) NS2022-2 |
The service chaining problem is one of the resource allocation problems in network functions virtualization (NFV) networ... [more] |
NS2022-2 pp.7-12 |
CQ, IMQ, MVE, IE (Joint) [detail] |
2022-03-09 10:10 |
Online |
Online (Zoom) |
A study on player and ball tracking in tennis videos. Kosuke Matsumoto (Kobe univ.), Junki Tamae (iret), Nobutaka Kuroki (Kobe univ.), Kensuke Hirano (iret), Masahiro Numa (Kobe univ.) IMQ2021-16 IE2021-78 MVE2021-45 |
This paper proposes a player and ball tracking method in tennis videos with image processing techniques. The proposed me... [more] |
IMQ2021-16 IE2021-78 MVE2021-45 pp.33-38 |
IBISML |
2022-03-08 13:05 |
Online |
Online |
[Invited Talk]
--- Takashi Matsubara (Osaka Univ.) IBISML2021-34 |
Deep learning is being considered as the most promising approach to building an artificial intelligence (AI) system; it ... [more] |
IBISML2021-34 p.27 |
IBISML |
2022-03-09 10:15 |
Online |
Online |
[Invited Talk]
--- Takahiro Tsukahara (Tokyo University of Science) IBISML2021-41 |
Turbulence of viscoelastic fluids, such as dilute polymer/surfactant solutions, is of practical importance, because it c... [more] |
IBISML2021-41 p.34 |
VLD, HWS [detail] |
2022-03-07 15:30 |
Online |
Online |
High-throughput In-Memory Accelerator for Binarized Neural Network based on 8T-SRAM Hiroto Tagata, Hiromitsu Awano (Kyoto Univ.) VLD2021-88 HWS2021-65 |
An in-memory accelerator for binary deep neural networks is presented.
The proposed circuit doubled the execution spee... [more] |
VLD2021-88 HWS2021-65 pp.63-68 |
AI |
2022-02-28 15:00 |
Miyazaki |
Youth Hostel Sunflower MIYAZAKI (Primary: On-site, Secondary: Online) |
Basic Study for Backdoor Attack based on Invisible Trigger Ryo Kumagai, Shu Takemoto, Yusuke Nozaki, Masaya Yoshikawa (Meijo Univ.) AI2021-21 |
A backdoor attack is a threat to deep neural networks (DNN). In an attack on a DNN for the purpose of image classificati... [more] |
AI2021-21 pp.53-58 |
IE, ITS, ITE-AIT, ITE-ME, ITE-MMS [detail] |
2022-02-21 13:15 |
Online |
Online |
Towards Universal Deep Image Compression Koki Tsubota (UTokyo), Hiroaki Akutsu (Hitachi), Kiyoharu Aizawa (UTokyo) ITS2021-31 IE2021-40 |
In this paper, we investigate deep image compression towards universal usage. In image compression, it is desirable to b... [more] |
ITS2021-31 IE2021-40 pp.37-42 |
RECONF, VLD, CPSY, IPSJ-ARC, IPSJ-SLDM [detail] |
2022-01-24 15:55 |
Online |
Online |
Accelerating Deep Neural Networks on Edge Devices by Knowledge Distillation and Layer Pruning Yuki Ichikawa, Akira Jinguji, Ryosuke Kuramochi, Hiroki Nakahara (Titech) VLD2021-58 CPSY2021-27 RECONF2021-66 |
A deep neural network (DNN) is computationally expensive, making it challenging to run DNN on edge devices. Therefore, m... [more] |
VLD2021-58 CPSY2021-27 RECONF2021-66 pp.49-54 |
RECONF, VLD, CPSY, IPSJ-ARC, IPSJ-SLDM [detail] |
2022-01-24 17:10 |
Online |
Online |
Ternarizing Deep Spiking Neural Network Man Wu, Yirong Kan, Van_Tinh Nguyen, Renyuan Zhang, Yasuhiko Nakashima (NAIST) VLD2021-61 CPSY2021-30 RECONF2021-69 |
The feasibility of ternarizing spiking neural networks (SNNs) is studied in this work toward trading a slight accuracy f... [more] |
VLD2021-61 CPSY2021-30 RECONF2021-69 pp.67-72 |