Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU |
2020-12-18 15:25 |
Online |
Online |
Multi-Task Attention Learning for Fine-grained Recognition Dichao Liu (NU), Yu Wang (Rits), Kenji Mase (NU), Jien Kato (Rits) PRMU2020-63 |
Due to its inter-class similarity and intra-class variation, Fine-Grained Image Classification (FGIC) is an intrinsicall... [more] |
PRMU2020-63 pp.145-150 |
PRMU |
2020-12-18 16:30 |
Online |
Online |
Estimating 3D regions for grasping an object Atsuki Tsukamoto, Kiyoshi Kogure (KIT) PRMU2020-65 |
This paper proposes a method for estimating 3D regions for object grasping. The method takes as its inputs two RGB image... [more] |
PRMU2020-65 pp.156-160 |
SITE, ISEC, HWS, EMM, BioX, IPSJ-CSEC, IPSJ-SPT, ICSS [detail] |
2020-07-20 10:50 |
Online |
Online |
Development of Feature Extractor for Visible Light Iris Recognition Using Deep Learning Tetsuya Honda, Hironobu Takano (Toyama Pref. Univ.) ISEC2020-16 SITE2020-13 BioX2020-19 HWS2020-9 ICSS2020-3 EMM2020-13 |
Biometric authentication is superior to other personal authentication methods in terms of security
against theft and co... [more] |
ISEC2020-16 SITE2020-13 BioX2020-19 HWS2020-9 ICSS2020-3 EMM2020-13 pp.15-19 |
NC, MBE (Joint) |
2020-03-05 09:30 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Improving Adversarial Robustness Based on Adversarial Training Consideration Ryota Komiyama, Motonobu Hattori (Univ. of Yamanashi) NC2019-90 |
Neural networks are used for various tasks because of their high performance.
However, it is known that even a high-per... [more] |
NC2019-90 pp.83-88 |
IBISML |
2020-01-09 13:50 |
Tokyo |
ISM |
Dimensionality reduction method for gaussian process posteriors based on information geometry Hideaki Ishibashi (Kyutech), Shotaro Akaho (AIST/RIKEN) IBISML2019-20 |
This paper proposes an extension of principal component analysis for gaussian process posteriors which is denoted by GP-... [more] |
IBISML2019-20 pp.17-24 |
HIP |
2019-12-19 14:00 |
Miyagi |
RIEC, Tohoku University |
Mathematical Representation of Emotion by Combining Recognition and Unification Tasks Using Multimodal Deep Neural Networks Seiichi Harata, Takuto Sakuma, Shohei Kato (NITech) HIP2019-65 |
To emulate human emotions in robots, the mathematical representation of emotion is important for all components of affec... [more] |
HIP2019-65 pp.1-6 |
AI |
2019-09-14 09:55 |
Kagoshima |
|
Fishing Spot Estimation by Using Sea Temperature Pattern Takumi Shimura, Motoharu Sonogashira, Hidekazu Kasahara, Masaaki Iiyama (Kyoto Univ.) AI2019-27 |
(To be available after the conference date) [more] |
AI2019-27 pp.45-49 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 17:25 |
Okinawa |
Okinawa Institute of Science and Technology |
Predicting Demographic Attributes for Individual Viewing Behavior Yusuke Kumagae, Ryoma Yasunaga, Ryo Fujii, Ryo Domoto (Hakuhodo) IBISML2019-10 |
User attribute estimation based on behaviors is an important task in marketing. Previous works have tried to estimate at... [more] |
IBISML2019-10 pp.65-71 |
PRMU |
2018-12-14 10:00 |
Miyagi |
|
Simultaneous Estimation of Facial Landmark and Attributes with Separation Multi-task Networks Ryo Matsui, Takayoshi Yamashita, Hironobu Fujiyoshi (Chubu Univ.) PRMU2018-82 |
(To be available after the conference date) [more] |
PRMU2018-82 pp.39-44 |
PRMU, BioX |
2018-03-18 11:10 |
Tokyo |
|
Simultaneous Learning Model of Food Image Recognition and Ingrediensts Estimation Koyo Ito, Takao Yamanaka (Sophia Univ.) BioX2017-38 PRMU2017-174 |
In recent years, many health-care applications such as food diary have been developed for smart devices. It is important... [more] |
BioX2017-38 PRMU2017-174 pp.13-18 |
IBISML |
2018-03-05 17:00 |
Fukuoka |
Nishijin Plaza, Kyushu University |
Transformed Multiple Matrix Factorization: Towards Utilizing Heterogeneous Auxiliary Information Taira Tsuchiya (Waseda Univ.), Tomoharu Iwata (NTT), Tetsuji Ogawa (Waseda Univ.) IBISML2017-96 |
Matrix factorization is widely used for a variety of fields, such as computer vision, document analysis, signal processi... [more] |
IBISML2017-96 pp.41-48 |
HCGSYMPO (2nd) |
2017-12-13 - 2017-12-15 |
Ishikawa |
THE KANAZAWA THEATRE |
Evaluation of draw-attention stimulus supporting Multi-task Yoshiki Suzuki, Yoshimasa Ohmoto (Kyoto Univ.), Sho Otaki, Hiroki Mori (TMC), Toyoaki Nishida (Kyoto Univ.) |
Today, technologies like AR applications tending to be used in parallel with conventional activities are spreading, and ... [more] |
|
IBISML |
2017-11-10 13:00 |
Tokyo |
Univ. of Tokyo |
[Poster Presentation]
Multi-Task Learning with Positive and Unlabeled Data and Its Application to Mental State Prediction Hirotaka Kaji, Hayato Yamaguchi (Toyota Motor), Masashi Sugiyama (RIKEN/UTokyo) IBISML2017-66 |
In real-world machine learning applications, we are often faced with a situation where only a small number of training s... [more] |
IBISML2017-66 pp.235-242 |
NC, IPSJ-BIO, IBISML, IPSJ-MPS [detail] |
2017-06-25 11:25 |
Okinawa |
Okinawa Institute of Science and Technology |
Cost-sensitive Bayesian optimization for multiple objectives and its application to material science Tomohiro Yonezu (NITech), Tomoyuki Tamura, Ryo Kobayashi (NITech/NIMS), Ichiro Takeuchi (NITech/NIMS/RIKEN), Masayuki Karasuyama (NITech/NIMS/JST) IBISML2017-10 |
We consider solving a set of black-box optimization problems in which each problem has a similar objective function each... [more] |
IBISML2017-10 pp.207-213 |
PRMU, SP |
2017-06-22 15:15 |
Miyagi |
|
Comparisons on Transplant Emotional Expressions in DNN-based TTS Synthesis Katsuki Inoue, Sunao Hara, Masanobu Abe (Okayama Univ.), Nobukatsu Hojo, Yusuke Ijima (NTT) PRMU2017-29 SP2017-5 |
Recent studies have shown that DNN-based speech synthesis can generate more natural synthesized speech than the conventi... [more] |
PRMU2017-29 SP2017-5 pp.23-28 |
NLC, TL |
2017-06-10 10:00 |
Tottori |
Tottori University |
General-Purpose Oriented Extended Named Entity Labeling of Wikipedia Entries Sakae Mizuki, Takeshi Sakaki (HTL) TL2017-9 NLC2017-9 |
In this research, we develop a classification method that assigns fine-grained named entity labels to entries of Wikiped... [more] |
TL2017-9 NLC2017-9 pp.47-52 |
NLC, IPSJ-IFAT |
2017-02-10 09:25 |
Osaka |
|
Extractive Summarization of Financial Statement Using Multi-Task Learning Masaru Isonuma, Toru Fujino, Jumpei Ukita, Haruka Murakami, Kimitaka Asatani, Junichiro Mori, Ichiro Sakata (UTokyo) NLC2016-47 |
In this paper, we proposed a methodology of summarizing financial statements which contributes to high quality investmen... [more] |
NLC2016-47 pp.45-50 |
IBISML |
2016-11-16 15:00 |
Kyoto |
Kyoto Univ. |
Additive Model Decomposition with Global Sparse Structure for Multi-task Granger Causal Estimation Hitoshi Abe, Jun Sakuma (Univ. Tsukuba) IBISML2016-56 |
Causality estimation is one of the key issues in time-series data analysis.
Granger causality is widely known as a form... [more] |
IBISML2016-56 pp.73-79 |
IBISML |
2015-11-27 14:00 |
Ibaraki |
Epochal Tsukuba |
[Poster Presentation]
Non-parametric tensor learning with Gaussian process prior and its application to multi-task learning Heishiro Kanagawa, Taiji Suzuki (Titech) IBISML2015-89 |
低ランクテンソル推定は複数のデータソース間の高次の関係性を学習する方法として,マルチタスク学習,
推薦システム,時空間解析など様々な問題に応用されている.低ランクテンソルを推定する代表的な手法として,線
形のモデルを仮定した凸最適化に基... [more] |
IBISML2015-89 pp.273-280 |
NC |
2015-01-29 16:30 |
Fukuoka |
Kyushu Institute of Technology |
Implementation of the higher-rank of SOM using formal neurons Yuta Saho, Kiyohisa Natsume, Tetsuo Furukawa (Kyutech) NC2014-62 |
The purpose of this work is building a neural network model which performs meta-model learning. The term `meta-model lea... [more] |
NC2014-62 pp.27-32 |