Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA |
2024-05-22 13:00 |
Online |
Online |
Trends in Sound Source Separation and Enhancement at ICASSP2024 Yoshiki Masuyama (TMU) |
(To be available after the conference date) [more] |
|
EA |
2024-05-22 16:50 |
Online |
Online |
[Invited Talk]
Fundamentals of Diffusion-based Generative Models and their Application to Speech Enhancement and Separation Scheibler Robin (LY Corp.) |
(To be available after the conference date) [more] |
|
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 14:25 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Extension of Young's Reaction-Diffusion Cellular Automaton and its Phenomena Taisei Nagashima, Tadashi Tsubone (NUT) MSS2023-93 NLP2023-145 |
(To be available after the conference date) [more] |
MSS2023-93 NLP2023-145 pp.107-110 |
NC, MBE (Joint) |
2024-03-12 13:30 |
Tokyo |
The Univ. of Tokyo (Primary: On-site, Secondary: Online) |
Diffusion-Based Immediate Adversarial Purification Yuito Narisawa, Motonobu Hattori (Yamanashi Univ.) NC2023-56 |
Neural networks have achieved high performance in image classification, but there is a problem known as Adversarial Exam... [more] |
NC2023-56 pp.75-80 |
MI |
2024-03-03 09:05 |
Okinawa |
OKINAWAKEN SEINENKAIKAN (Primary: On-site, Secondary: Online) |
[Short Paper]
Generation of Counterfactual Pathology Images of Malignant Lymphoma using Diffusion Models Ryoichi Koga, Tatsuya Yokota (NIT), Kouichi Ohshima, Hiroaki Miyoshi, Miharu Nagaishi (Kurume Univ.), Noriaki Hashimoto (RIKEN), Ichiro Takeuchi (Nagoya Univ.), Hidekata Hontani (NIT) MI2023-30 |
Malignant lymphoma has more than 70 subtypes. In the pathological diagnosis, a pathological image is observed to identif... [more] |
MI2023-30 pp.1-2 |
PRMU, IBISML, IPSJ-CVIM |
2024-03-04 10:52 |
Hiroshima |
Hiroshima Univ. Higashi-Hiroshima campus (Primary: On-site, Secondary: Online) |
Illust Protection against Generative AI using DnCNN Yukiya Fukuda, Daiju Kanaoka (Kyutech), Hakaru Tamukoh (Kyutech/Research Center for Neuromorphic AI Hardware) PRMU2023-71 |
Although generative AI such as stable diffusion are rapidly developing, but there are concerns about problems such as un... [more] |
PRMU2023-71 pp.116-121 |
MI |
2024-03-04 09:48 |
Okinawa |
OKINAWAKEN SEINENKAIKAN (Primary: On-site, Secondary: Online) |
A trial for improvement in image quality of cone-beam CT images using conditional diffusion model Naruki Murahashi, Mitsuhiro Nakamura, Megumi Nakao (Kyoto Univ.) MI2023-66 |
In this study, we propose a method to improve the image quality of CBCT images based on a conditional diffusion model th... [more] |
MI2023-66 pp.109-112 |
ITS, IE, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2024-02-20 11:00 |
Hokkaido |
Hokkaido Univ. |
Image Generation Modification with Diffusion Model through Sketch Guidance Sandra Zhang Ding, Jiafeng Mao, Kiyoharu Aizawa (UTokyo) ITS2023-64 IE2023-53 |
Large-scale image generation models have demonstrated their remarkable ability to generate diverse, high-quality images.... [more] |
ITS2023-64 IE2023-53 pp.95-99 |
CQ, CBE (Joint) |
2024-01-25 15:35 |
Kumamoto |
Kurokawa-Onsen (Primary: On-site, Secondary: Online) |
On Inhibition of Self-interested Behavior in Collective Action Problem Triggered by Dissemination of Corrective Information Masaaki Miyashita, Norihiko Shinomiya (Soka Univ.) CQ2023-57 |
The collective action problem, in which misinformation prompts individuals to engage in self-interested behavior, which ... [more] |
CQ2023-57 pp.31-36 |
HCGSYMPO (2nd) |
2023-12-11 - 2023-12-13 |
Fukuoka |
Asia pacific Import Mart (Kitakyushu) (Primary: On-site, Secondary: Online) |
Creating cover images using characteristic words from online novels and image generative AI Yuki Ishida, Tomoko Kajiyama (Hiroshima City Univ.), Shin'ichi Satoh (NII) |
Because many web novels do not have cover images that intuitively convey the content to readers, it is difficult to disc... [more] |
|
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 14:40 |
Tottori |
(Primary: On-site, Secondary: Online) |
Diffusion-based Geometric Unwarping and Illumination Correction for Document Images Sota Imahayashi, Guoqing Hao, Satoshi Iizuka, Kazuhiro Fukui (Univ. of Tsukuba) PRMU2023-36 |
This study proposes a method to improve the visibility of document images by correcting distortions and re-illuminating ... [more] |
PRMU2023-36 pp.113-118 |
RISING (3rd) |
2023-10-31 09:45 |
Hokkaido |
Kaderu 2・7 (Sapporo) |
[Poster Presentation]
Triadic Split Computing toward Privacy-Conscious Generative AI services Shoki Ohta, Takayuki Nishio (Tokyo Tech) |
With the rapid advancements in big AI models such as text and image generation models, numerous web services have begun ... [more] |
|
MIKA (3rd) |
2023-10-10 15:35 |
Okinawa |
Okinawa Jichikaikan (Primary: On-site, Secondary: Online) |
[Poster Presentation]
An Evaluation of the Generalizability of Influencer Prediction Models between Social Networks in Different Domains Kota Tahara, Sho Tsugawa (ITF) |
Identifying influencers on social media is one of the important research issues. Various methods for identifying influen... [more] |
|
NLP, CAS |
2023-10-07 10:50 |
Gifu |
Work plaza Gifu |
Characteristics of traveling waves in inhomogeneous media with FitzHugh-Nagumo model
-- focusing on dispersion relations and percolation transition -- Chikoo Oosawa (Kyushu Inst. of Tech.) CAS2023-51 NLP2023-50 |
Numerical solutions were obtained from FitzHugh-Nagumo(FHN) model in a two-dimensional media. In order to introduce hete... [more] |
CAS2023-51 NLP2023-50 pp.96-99 |
AI |
2023-09-12 15:55 |
Hokkaido |
|
Analysis of Conditional Image Generation Methods Using Color Palettes in Animal Personification Task Jianglin Xu, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC) AI2023-19 |
With the advent of large-scale pre-trained open-source diffusion models, image generation is now easily accessible to no... [more] |
AI2023-19 pp.101-108 |
AI |
2023-09-12 15:35 |
Hokkaido |
|
Variational Autoencoder Oriented Protection for Intellectual Property Ryo Kumagai, Shu Takemoto, Yusuke Nozaki, Masaya Yoshikawa (Meijo Univ.) AI2023-31 |
In recent years, generative AI, which generates images based on instructions in natural language, has developed rapidly ... [more] |
AI2023-31 pp.180-186 |
AI |
2023-09-12 16:50 |
Hokkaido |
|
Koki Miyauchi, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC) AI2023-34 |
Icons are indispensable elements for websites and smartphone applications. For website developers, the creation of icons... [more] |
AI2023-34 pp.201-206 |
MSS, CAS, SIP, VLD |
2023-07-07 15:20 |
Hokkaido |
(Primary: On-site, Secondary: Online) |
Verification of effectiveness of the greedy algorithm for the influence maximization problem focusing on the authenticity in OSN Jodai Yoshiue, Atsushi Wakamatsu, Masaaki Miyasita, Norihiko Shinomiya (Soka Univ.) CAS2023-28 VLD2023-28 SIP2023-44 MSS2023-28 |
In recent years, social media has become increasingly popular. While it has advantages such as high advertising effectiv... [more] |
CAS2023-28 VLD2023-28 SIP2023-44 MSS2023-28 pp.143-146 |
MI |
2023-07-03 10:00 |
Miyagi |
Tohoku Univ. Sakura Hall |
HCP data processing by hybrid approach for parameter inference in free water imaging model of diffusion MRI
-- comparison of diffusion tensor computation methods for datasets without b0 image -- Yoshitaka Masutani (Tohoku Univ.), Keigo Yamazaki, Wataru Uchida, Koji Kamagata (Juntendo Univ.), Koh Sasaki (HHC), Shigeki Aoki (Juntendo Univ.) MI2023-7 |
We have proposed a hybrid approach combining synthetic Q-space learning and conventional fitting for parameter estimatio... [more] |
MI2023-7 pp.1-2 |