Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
MI |
2021-03-15 15:15 |
Online |
Online |
Deep State-Space Modeling of FMRI Images with Disentangle Attributes Koki Kusano (Kobe Univ.), Takashi Matsubara (Osaka Univ.), Kuniaki Uehara (Osaka Gakuin Univ.) MI2020-59 |
As well as the disorder and other targets, nuisance attributes such as age, gender, and scanner specifications underlie ... [more] |
MI2020-59 pp.56-61 |
MI |
2021-03-17 13:45 |
Online |
Online |
Medical Image Style Translation by Adversarial Training with Paired Inputs Kazuki Fujioka (Kobe Univ.), Takashi Matsubara (Osaka Univ.), Kuniaki Uehara (Osaka Gakuin Univ.) MI2020-96 |
Medical image diagnosis by artificial intelligence requires a large amount of data for learning. However, preparing such... [more] |
MI2020-96 pp.212-217 |
IBISML |
2020-10-20 10:25 |
Online |
Online |
Few-shot Anomaly Detection by Extracting Common Feature of Set Data Kazuki Sato (Kobe Univ.), Satoshi Nakata (The KAITEKI Institute), Takashi Matsubara (Osaka Univ.), Kuniaki Uehara (Osaka Gakuin Univ.) IBISML2020-9 |
[more] |
IBISML2020-9 pp.8-13 |
IN, CCS (Joint) |
2020-08-03 15:35 |
Online |
Online |
[Invited Talk]
Current Status and Future Prospects for Image-Based Anomaly Detection Kazuki Sato (Kobe Univ.), Takashi Matsubara (Osaka Univ.), Kuniaki Uehara (Osaka Gakuin Univ.) CCS2020-12 |
[more] |
CCS2020-12 pp.1-4 |
IBISML |
2020-03-11 09:45 |
Kyoto |
Kyoto University (Cancelled but technical report was issued) |
Knowledge Graph Completion by Separating Transition and Score Functions Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-41 |
A knowledge graph is represented by a set of two entities and the relations, and used for various tasks such as informat... [more] |
IBISML2019-41 pp.59-62 |
IBISML |
2020-03-11 15:10 |
Kyoto |
Kyoto University (Cancelled but technical report was issued) |
Fairness Causes Vulnerability to Adversarial Attacks Koki Wataoka, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-48 |
When using machine learning models in society, it is essential to be ensure classifiers are fair to race and gender. In ... [more] |
IBISML2019-48 pp.101-105 |
CCS |
2019-11-14 13:25 |
Hyogo |
Kobe Univ. |
Calibration of Confidence in Deep Learning under Dataset Shift Kazuki Yoshida, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) CCS2019-25 |
Calibration of confidence is important when you want to obtain not only the prediction class of unknown data but also th... [more] |
CCS2019-25 pp.5-8 |
CCS |
2019-11-15 10:45 |
Hyogo |
Kobe Univ. |
Deep Unsupervised Defect Segmentation Robust to Aleatoric Uncertainty Kazuki Sato, Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) CCS2019-32 |
[more] |
CCS2019-32 pp.37-40 |
CCS |
2019-11-15 11:10 |
Hyogo |
Kobe Univ. |
Mental Disorder Diagnosis Based on fMRI Images by Deep Generative Model Using Attribute Koki Kusano, Tetsuo Tashiro, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) CCS2019-33 |
[more] |
CCS2019-33 pp.41-44 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 13:00 |
Okinawa |
Okinawa Institute of Science and Technology |
Reliability Assessment by Bayesian Deep Learning for Image-Caption Retrieval Task Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-1 |
Following the development of black-box machine learning algorithms, the practical demand of the re- liability assessment... [more] |
IBISML2019-1 pp.1-8 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 13:25 |
Okinawa |
Okinawa Institute of Science and Technology |
Adversarial Day-to-Night Conversion Supporting Object Detection for Autonomous Driving Kazuki Fujioka (Kobe Univ.), Takashi Machida (Toyota CRDL), Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-2 |
[more] |
IBISML2019-2 pp.9-14 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 13:50 |
Okinawa |
Okinawa Institute of Science and Technology |
Aleatoric Uncertainty-Aware Score for Deep Unsupervised Anomaly Segmentation Kazuki Sato, Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-3 |
[more] |
IBISML2019-3 pp.15-20 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 17:35 |
Okinawa |
Okinawa Institute of Science and Technology |
Mental Disorder Diagnosis Based on fMRI Images by Deep Privileged Attribute Model Koki Kusano, Tetsuo Tashiro, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) NC2019-12 |
Machine learning-based accurate diagnosis of mental disorders is expected to support finding their biomarkers and unders... [more] |
NC2019-12 pp.45-50 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 13:30 |
Okinawa |
Okinawa Institute of Science and Technology |
Hybrid Reinforcement and Imitation Learning for Human-Like Agents Rousslan Fernand Julien Dossa, Xinyu Lian (Kobe Uni), Hirokazu Nomoto (EQUOS RESEARCH), Takashi Matsubara, Kuniaki Uehara (Kobe Uni) NC2019-16 IBISML2019-14 |
Reinforcement learning methods achieve performance superior to humans in a wide range of complex tasks and uncertain env... [more] |
NC2019-16 IBISML2019-14 pp.69-74(NC), pp.91-96(IBISML) |
CCS |
2018-11-23 10:50 |
Hyogo |
Kobe Univ. |
A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning Xinyu Lian, Rousslan Fernand Julien Dossa (Kobe Univ.), Hirokazu Nomoto (EQUOS RESEARCH), Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) CCS2018-41 |
Reinforcement learning (RL) makes it possible to build an efficient agent that handles tasks in complex and uncertain en... [more] |
CCS2018-41 pp.45-50 |
CCS |
2018-11-23 14:55 |
Hyogo |
Kobe Univ. |
Hypernetwork-based Implicit Posterior Estimation of CNN Kenya Ukai, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) CCS2018-45 |
Deep neural networks have a rich ability to learn complex representations and achieved remarkable results in various tas... [more] |
CCS2018-45 pp.67-72 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2018-09-20 09:50 |
Fukuoka |
|
Image-Caption Retrieval by Embedding to Gaussian Distribution Kenta Hama, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) PRMU2018-38 IBISML2018-15 |
To get distributed representations of words, one has typically embedded words to points.
Recent studies successfully... [more] |
PRMU2018-38 IBISML2018-15 pp.17-20 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2018-09-20 09:40 |
Fukuoka |
|
Image Patchwork Data Augmentation Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) PRMU2018-43 IBISML2018-20 |
Deep convolutional neural networks (CNNs) have demonstrated remarkable results thanks to their numerous parameters.
How... [more] |
PRMU2018-43 IBISML2018-20 pp.47-54 |
IN, CCS (Joint) |
2018-08-02 13:50 |
Hokkaido |
Kitayuzawa Mori-no-Soraniwa |
Deep Generative Model Structured for Feature Extraction of fMRI Images Tetsuo Tashiro, Takashi Matsubara, Kuniaki Uehara (Kove Univ.) CCS2018-32 |
[more] |
CCS2018-32 pp.29-32 |
IN, ICTSSL, NWS (Joint) |
2016-10-20 11:25 |
Osaka |
Osaka Uinv. |
Reasoning daily activities of single life using environment sensing and indoor location Long Niu, Seiji Sakakibara, Seiki Tokunaga, Sachio Saiki, Takashi Matsubara, Masahide Nakamura, Kuniaki Uehara (Kobe Univ.) IN2016-49 |
[more] |
IN2016-49 pp.7-8 |