Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU |
2017-10-12 09:30 |
Kumamoto |
|
Accelerating Convolutional Neural Networks Using Low-Rank Tensor Decomposition Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota (Tokyo Inst. of Tech.) PRMU2017-63 |
In the image recognition using convolution neural networks (CNN), convolution operations occupies the majority of the co... [more] |
PRMU2017-63 pp.1-6 |
PRMU |
2017-10-12 10:00 |
Kumamoto |
|
Research on Automatic Nervous State Estimation based on Time-Series Deep Learning Kanji Yamaguchi, Masayuki Kashima, Shinya Fukumoto, Kiminori Satou, Mutsumi Watanabe (Kagoshima Univ.) PRMU2017-64 |
[more] |
PRMU2017-64 pp.7-12 |
PRMU |
2017-10-12 10:30 |
Kumamoto |
|
Extracting photographic subjects with deep learning and automatically select to best composition Soma Nagadome, Shigeki Aoki, Takao Miyamoto (Osaka Pref. Univ.) PRMU2017-65 |
Recently, opportunities for taking pictures are increasing, but many people are difficult to take pictures beautifully. ... [more] |
PRMU2017-65 pp.13-18 |
PRMU |
2017-10-12 11:00 |
Kumamoto |
|
Face identification based on shape spaces randomly generated from facial minute feature points Kazuki Takasaka, Kazuhiro Fukui (Tsukuba Univ.) PRMU2017-66 |
In this paper, we propose a face identification method based on the 3-d structure of facial minute feature points. The p... [more] |
PRMU2017-66 pp.19-24 |
PRMU |
2017-10-12 09:30 |
Kumamoto |
|
An Effective De-noising Algorithm for Making A Large Celebrity Face Dataset with A High Purity Zheng Ge, Quan Cui (Waseda Univ.), Rong Xu, Masahiro Imai (Datasection Inc.), Osamu Yoshie (Waseda Univ.) PRMU2017-67 |
In recent years, face recognition has been greatly improved by the development of CNN such as DeepID, FaceNet, and so on... [more] |
PRMU2017-67 pp.25-30 |
PRMU |
2017-10-12 10:00 |
Kumamoto |
|
Online Human Action Detection using Deep Spatio-temporal Transformation Yukihide Takagaki, Masaki Aono (TUT) PRMU2017-68 |
In this research, we describe online human action detection using Convolutional Neural Network which inputs skeleton dat... [more] |
PRMU2017-68 pp.31-35 |
PRMU |
2017-10-12 10:30 |
Kumamoto |
|
Indoor Area Estimation Using Convolutional Neural Network with Spectrogram of Environmental Ultrasound Tatsuro Tsuchiya, Takeshi Umezawa, Noritaka Osawa (Chiba Univ.) PRMU2017-69 |
Active methods for indoor position estimation have been proposed which are based on signal strength or propagation time ... [more] |
PRMU2017-69 pp.37-42 |
PRMU |
2017-10-12 11:00 |
Kumamoto |
|
Implementation and Performance Analysis of iOS Deep Learning Application using CoreML Ryosuke Tanno, Yuki Izumi, Keiji Yanai (UEC) PRMU2017-70 |
[more] |
PRMU2017-70 pp.43-48 |
PRMU |
2017-10-12 13:00 |
Kumamoto |
|
The Effectiveness of CNN feature for mutual subspace method Taku Nakayama, Kazuhiro Fukui (Univ. Tsukuba) PRMU2017-71 |
[more] |
PRMU2017-71 pp.49-54 |
PRMU |
2017-10-12 13:30 |
Kumamoto |
|
Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise (Osaka Pref. Univ.) PRMU2017-72 |
(To be available after the conference date) [more] |
PRMU2017-72 pp.55-60 |
PRMU |
2017-10-12 14:00 |
Kumamoto |
|
Entanglement Entropic Convolutional Neural Network Shu Eguchi, Masaru Tanaka (Fukuoka Univ.) PRMU2017-73 |
The neural network used for machine learning is an extract that extracts information necessary for classification from e... [more] |
PRMU2017-73 pp.61-66 |
PRMU |
2017-10-12 14:30 |
Kumamoto |
|
Generalized Subclass Method for Multi-label Classification Batzaya Norov-Erdene, Mineichi Kudo (Hokkaido Univ.) PRMU2017-74 |
Multi-label classification (MLC) problems are emerging in medical diagnosis, web page annotation, image annotation, etc.... [more] |
PRMU2017-74 pp.67-72 |
PRMU |
2017-10-12 13:00 |
Kumamoto |
|
CNN-based Estimation of Food Calories for Multiple-dish Food Photos Takumi Ege, Keiji Yanai (UEC) PRMU2017-75 |
[more] |
PRMU2017-75 pp.73-78 |
PRMU |
2017-10-12 13:30 |
Kumamoto |
|
Research on Adaptive Assistance Based on Situation Recognition of Robot Takaya Ono, Masayuki Kashima, Shinya Fukumoto, Kiminori Sato, Mutsumi Watanabe (Kagoshima Univ.) PRMU2017-76 |
In recent years, various communication robots have been developed and becoming familiar existence. Meanwhile, since comm... [more] |
PRMU2017-76 pp.79-84 |
PRMU |
2017-10-12 14:00 |
Kumamoto |
|
Self-state-aware convolutional neural network for autonomous driving Takuya Murase, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi (Chubu Univ.) PRMU2017-77 |
[more] |
PRMU2017-77 pp.85-90 |
PRMU |
2017-10-12 14:30 |
Kumamoto |
|
[Short Paper]
Research of Automatic Scene Segmentation for Video Summary Generation based on Deep Learning Yuki Futami, Masayuki Kashima, Shinya Fukumoto, Kiminori Sato, Mutsumi Watanabe (Kagoshima Univ.) PRMU2017-78 |
Huge amount of video contents are handled routinely.
The video is divided into scenes that consists of semantic cluster... [more] |
PRMU2017-78 pp.91-92 |
PRMU |
2017-10-12 14:45 |
Kumamoto |
|
[Short Paper]
A Study on Manga Object Recognition Mechanism by Convolution Neural Network Hideaki Yanagisawa, Takuro Yamashita, Hiroshi Watanabe (Waseda Univ.) PRMU2017-79 |
In order to make use of manga images on the internet, techniques to detect objects such as speech balloons and character... [more] |
PRMU2017-79 pp.93-94 |
PRMU |
2017-10-12 15:10 |
Kumamoto |
|
[Tutorial Lecture]
Families of GANs Tomohiro Takahashi (ABEJA) PRMU2017-80 |
Generative Adversarial Networks(GANs) have recently gained popularity due to their ability to synthesize images which ar... [more] |
PRMU2017-80 pp.95-100 |
PRMU |
2017-10-13 09:15 |
Kumamoto |
|
Improvement of speed using low precision arithmetic in deep learning and performance evaluation of accelerator Hiroki Naganuma, Akira Sekiya, Kazuki Osawa, Hiroyuki Ootomo, Yuji Kuwamura, Rio Yokota (Tokyo Inst. of Tech.) PRMU2017-81 |
While recent convolution neural networks (CNN)cite{ref:CNN} are improving performance, amout of computation and data vol... [more] |
PRMU2017-81 pp.101-107 |
PRMU |
2017-10-13 09:45 |
Kumamoto |
|
[Survey paper] Vision-based path prediction Tsubasa Hirakawa, Takayoshi Yamashita (Chubu Univ.), Toru Tamaki (Hiroshima Univ.), Hironobu Fujiyoshi (Chubu Univ.) PRMU2017-82 |
Path prediction is a method to predict future migration pathway of an object such as pedestrian or car in a movie. Becau... [more] |
PRMU2017-82 pp.109-118 |