Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM |
2023-05-19 15:40 |
Aichi |
(Primary: On-site, Secondary: Online) |
Object-Centric Representation Learning with Attention Mechanism Hidemoto Nakada, Hideki Asoh (AIST) PRMU2023-13 |
For object-centric representation learning, several slot-based methods, that separate objects using masks and learn the ... [more] |
PRMU2023-13 pp.68-73 |
PRMU, IPSJ-CVIM, IPSJ-NL |
2021-05-21 10:30 |
Online |
Online |
A Study on Domain Adaptation for Video Action Classification Utilizing Synthetic Data. Hana Isoi (Ochanomizu Univ.), Atsuko Takefusa (NII), Hidemoto Nakada (AIST), Masato Oguchi (Ochanomizu Univ.) PRMU2021-5 |
The lack of learning data is considered as one of the reasons why the classification accuracies of deep neural networks ... [more] |
PRMU2021-5 pp.25-30 |
PRMU |
2020-09-02 16:30 |
Online |
Online |
Representation Learning using Video Frame Prediction and Contrastive Learning Hidemoto Nakada, Hideki Asoh (AIST) PRMU2020-17 |
The recent development in the unsupervised learning area enabled accuracy in the downstream tasks that equal the one wit... [more] |
PRMU2020-17 pp.59-64 |
CPSY, DC, IPSJ-ARC [detail] |
2020-07-30 14:30 |
Online |
Online |
Distributed Runtime Environment with Julia Language Hidemoto Nakada (AIST) CPSY2020-2 DC2020-2 |
Julia-lang is a relatively new scripting language aiming at high-performance computing powered by powerful LLVM JIT comp... [more] |
CPSY2020-2 DC2020-2 pp.9-14 |
IBISML |
2020-03-11 11:35 |
Kyoto |
Kyoto University (Cancelled but technical report was issued) |
Pre-training for Action Classification Task Using Video Frame Prediction Task Hidemoto Nakada, Hideki Asoh (AIST) IBISML2019-45 |
Continuous Video frames have strongly correlated with each other and thus include rich information that could be leverag... [more] |
IBISML2019-45 pp.85-90 |
VLD, DC, CPSY, RECONF, ICD, IE, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC (Joint) [detail] |
2019-11-14 15:45 |
Ehime |
Ehime Prefecture Gender Equality Center |
Chikako Takasaki (Ocha Univ.), Atsuko Takefusa (NII), Hidemoto Nakada (AIST), Masato Oguchi (Ocha Univ.) CPSY2019-43 |
(To be available after the conference date) [more] |
CPSY2019-43 pp.7-12 |
PRMU, BioX |
2019-03-17 15:15 |
Tokyo |
|
Arbitrary Charactor Image Generation in Arbitrary Poses using Neural Network Hidemoto Nakada, Hideki Asoh (AIST) BioX2018-41 PRMU2018-145 |
Thanks to recent improvement of image generation technologies by neural networks, now we can gener- ate photo-realistic ... [more] |
BioX2018-41 PRMU2018-145 pp.73-78 |
CPSY, DC, IPSJ-ARC (Joint) [detail] |
2018-08-01 15:45 |
Kumamoto |
Kumamoto City International Center |
Asynchronous Deep Learning Test-bed to Analyze Gradient Staleness Effect Duo Zhang (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada (AIST) CPSY2018-27 |
For modern machine learning systems, including deep learning systems, parallelization is inevitable since they are requi... [more] |
CPSY2018-27 pp.199-204 |
CPSY, DC, IPSJ-ARC (Joint) [detail] |
2018-08-01 16:15 |
Kumamoto |
Kumamoto City International Center |
Adaptation of Ray, a distributed framework for machine learning, to MPI-based environment Tianlun Wang (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada (AIST) CPSY2018-28 |
Ray is a distributed framework for machine learning that targets reinforcement learning using multiple nodes. While it w... [more] |
CPSY2018-28 pp.205-210 |
PRMU, BioX |
2018-03-18 16:10 |
Tokyo |
|
Toward image inbetweening using Latent Model Paulino Cristovao (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada, Hideki Asoh (AIST) BioX2017-49 PRMU2017-185 |
Image interpolation is a well known problem in computer vision. Many approaches are restricted to optical flow and convo... [more] |
BioX2017-49 PRMU2017-185 pp.79-84 |
PRMU, BioX |
2018-03-18 17:10 |
Tokyo |
|
A Style Transfer Method using Variational Autoencoder Hidemoto Nakada, Hideki Asoh (AIST) BioX2017-56 PRMU2017-192 |
Image Style Transfer is a technique to render arbitrary image content with
arbitrary image 'style'.
Most existing... [more] |
BioX2017-56 PRMU2017-192 pp.121-126 |
MoNA |
2017-12-21 15:20 |
Tokyo |
Ochanomizu University |
Consideration on the Structure of Real-time Video Analysis Framework using Kafka and Spark Streaming Ayae Ichinose (Ochanomizu Univ.), Atsuko Takefusa (NII), Hidemoto Nakada (AIST), Masato Oguchi (Ochanomizu Univ.) MoNA2017-39 |
As the use of various sensors and cloud computing technologies has spread, many life-log analysis applications for safet... [more] |
MoNA2017-39 pp.59-63 |
MoNA |
2017-12-21 15:45 |
Tokyo |
Ochanomizu University |
Consideration of Parallel Data Processing over an Apache Spark, a large-scale data distributed platform Kasumi Kato (Ocha Univ.), Atsuko Takefusa (NII), Hidemoto Nakada (AIST), Masato Oguchi (Ocha Univ.) MoNA2017-40 |
The Spread of cameras and sensors and cloud technologies enable us to obtain life logs at ordinary homes and transmit th... [more] |
MoNA2017-40 pp.65-69 |
CPSY, DC, IPSJ-ARC (Joint) [detail] |
2017-07-27 17:00 |
Akita |
Akita Atorion-Building (Akita) |
A study on Network Structure and Parameter Exchange Method in large-scale Cluster for Machine Learning Duo Zhang, Mingxi Li (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada (AIST) CPSY2017-29 |
For modern machine learning systems, including deep learning systems, parallelization is inevitable since they are requi... [more] |
CPSY2017-29 pp.145-150 |
NC, NLP (Joint) |
2017-01-27 13:50 |
Fukuoka |
Kitakyushu Foundation for the Advanement of Ind. Sci. and Tech. |
Toward Context-Dependent Robust Character Recognition using Large-scale Restricted Bayesian Network Hidemoto Nakada, Yuuji Ichisugi (AIST) NC2016-59 |
We have been proposing a computational model of the cerebral cortex called BESOM,
that models the cerebral cortex as r... [more] |
NC2016-59 pp.65-70 |
DE, CEA |
2016-12-01 15:55 |
Tokyo |
|
A Spark SQL Extension to utilize MLlib from SQL Hidemoto Nakada, Hirotaka Ogawa (AIST) DE2016-30 |
[more] |
DE2016-30 pp.51-56 |
CPSY, DC, IPSJ-ARC (Joint) [detail] |
2016-08-08 17:30 |
Nagano |
Kissei-Bunka-Hall (Matsumoto) |
Toward improving I/O performance of Spark RDD Kaihui Zhang (Tsukuba Univ.), Yusuke Tanimura, Hidemoto Nakada, Hirotaka Ogawa (AIST) CPSY2016-16 |
[more] |
CPSY2016-16 pp.77-82 |
CPSY, DC, IPSJ-ARC (Joint) [detail] |
2016-08-09 11:15 |
Nagano |
Kissei-Bunka-Hall (Matsumoto) |
A simulation study on fault tolerancy of parallel machine learning systems with parameter servers Mingxi Li (Univ. of Tsukuba), Yusuke Tanimura, Hidemoto Nakada (AIST) CPSY2016-20 DC2016-17 |
Parallel computation is essential for machine learning systems to be more faster.
There are two techniques to build par... [more] |
CPSY2016-20 DC2016-17 pp.125-130(CPSY), pp.1-6(DC) |
VLD, CPSY, RECONF, IPSJ-SLDM, IPSJ-ARC [detail] |
2016-01-19 13:55 |
Kanagawa |
Hiyoshi Campus, Keio University |
GPGPU Parallelization of a cerebral cortex model BESOM Hidemoto Nakada, Tatsuhiko Inoue, Yuji Ichisugi (AIST) VLD2015-82 CPSY2015-114 RECONF2015-64 |
[more] |
VLD2015-82 CPSY2015-114 RECONF2015-64 pp.31-36 |
DE |
2015-09-25 10:30 |
Kanagawa |
|
Performance Evaluation of Load Balancing between Sensors and a Cloud for a Real Time Video Streaming Analysis Application Framework Yuko Kurosaki (Ochanomizu Univ.), Atsuko Takefusa, Hidemoto Nakada (AIST), Masato Oguchi (Ochanomizu Univ.) DE2015-24 |
(To be available after the conference date) [more] |
DE2015-24 pp.23-28 |