Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU |
2018-12-13 10:00 |
Miyagi |
|
Style conversion Miduki Mori, Toshiki Nakamura, Hideaki Hayashi, Seiichi Uchida (Kyushu Univ.) PRMU2018-75 |
In this research, in order to find the boundary between handwritten character and typeface, we attempt to acquire a func... [more] |
PRMU2018-75 pp.1-6 |
PRMU |
2018-12-13 10:15 |
Miyagi |
|
Toshiki Nakamura, Seiichi Uchida (Kyushu Univ.) PRMU2018-76 |
The purpose of this research is magnifying scene texts using convolutional neural network (CNN) with end-to-end.
We tr... [more] |
PRMU2018-76 pp.7-12 |
PRMU |
2018-12-13 10:30 |
Miyagi |
|
Candidate Reduction Method Using Hierarchical Overlapping Clustering and Convolutional Neural Network for Fast Chinese Character Recognition Soichi Tashima, Hideaki Goto (Tohoku Univ.) PRMU2018-77 |
Along with the widespread of the mobile devices equipped with cameras, many applications using the camera function have ... [more] |
PRMU2018-77 pp.13-18 |
PRMU |
2018-12-13 10:45 |
Miyagi |
|
An attention-based encoder-decoder for recognizing Japanese historical document recognition Le Duc Anh (CODH), Mochihashi daichi (ISM), Masuda katsuya, Mima Hideki (UT) PRMU2018-78 |
Inspired by the recent successes of attention based encoder-decoder (AED) approach on image captioning, machine translat... [more] |
PRMU2018-78 pp.19-22 |
PRMU |
2018-12-13 14:40 |
Miyagi |
|
Extracting rules from convolutional neural networks Hiroshi Tsukimoto, Yuya Sato (Tokyo Denki Univ.) PRMU2018-79 |
To understand the inner structures of convolutional neural networks, several techniques of visualization have been devel... [more] |
PRMU2018-79 pp.23-28 |
PRMU |
2018-12-13 14:55 |
Miyagi |
|
Fast Distributional Smoothing for CTC-VAT and its Application to Text Line Recognition Ryohei Tanaka, Soichiro Ono, Akio Furuhata (Toshiba Digital Solutions) PRMU2018-80 |
Virtual Adversarial Training (VAT), which smooths posterior distribution by minimizing distributional distance of poster... [more] |
PRMU2018-80 pp.29-34 |
PRMU |
2018-12-13 15:10 |
Miyagi |
|
PRMU2018-81 |
Although recent progress in machine learning has substantially improved the accuracy of pattern recognition task, the pe... [more] |
PRMU2018-81 pp.35-38 |
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 |
2018-12-14 10:15 |
Miyagi |
|
Buried Object Detection From Ground Penetrating Radar Image Using YOLO Yusuke Hamano, Tomoyuki Kimoto (National Institute of Technology, Oita College), Jun Sonoda (National Institute of Technology, Sendai College) PRMU2018-83 |
[more] |
PRMU2018-83 pp.45-50 |
PRMU |
2018-12-14 10:30 |
Miyagi |
|
Detection of Partially Occluded Flowers for Robotic Pollination Ryo Sato, Gustavo Alfonso Garcia Ricardez, Jun Takamatsu, Tsukasa Ogasawara (NAIST) PRMU2018-84 |
In robotic pollination, detection of partially occluded flowers from a certain viewpoint is very important for making a ... [more] |
PRMU2018-84 pp.51-56 |
PRMU |
2018-12-14 10:45 |
Miyagi |
|
[Short Paper]
Calving prediction using behavioral information from video Kazuma Sugawara (Waseda Univ.), Teppei Nakano, Makoto Akabane (Waseda Univ./IFLab), Tetsunori Kobayashi, Tetsuji Ogawa (Waseda Univ.) PRMU2018-85 |
This study presents calving prediction methods focusing on cows' pre-calving behaviors and their changes.
Livestock far... [more] |
PRMU2018-85 pp.57-60 |
PRMU |
2018-12-14 11:00 |
Miyagi |
|
[Short Paper]
Skeleton-based Human Action Recognition with Fine-to-Coarse Convolutional Neural Network Thao Minh Le, Nakamasa Inoue, Koichi Shinoda (TokyoTech) PRMU2018-86 |
This work introduces a new framework for skeleton-based human action recognition. Existing approaches using Convolutiona... [more] |
PRMU2018-86 pp.61-64 |
PRMU |
2018-12-14 13:00 |
Miyagi |
|
PRMU2018-87 |
(To be available after the conference date) [more] |
PRMU2018-87 p.65 |
PRMU |
2018-12-14 14:10 |
Miyagi |
|
What Affects Visual Ad Clicks in Social Media Platforms? Yuki Iwazaki, Kota Yamaguchi (CyberAgent, Inc.) PRMU2018-88 |
In the online advertisement, high-quality prediction on click-through rate (CTR) is crucial for delivering the optimal a... [more] |
PRMU2018-88 pp.67-72 |
PRMU |
2018-12-14 14:25 |
Miyagi |
|
Training of Traffic Sign Detector and Classifier Using Synthetic Road Scenes Akira Sekizawa, Katsuto Nakajima (TDU) PRMU2018-89 |
This paper proposes a method of providing an end-to-end object recognition system based on deep learning that uses synth... [more] |
PRMU2018-89 pp.73-78 |
PRMU |
2018-12-14 14:40 |
Miyagi |
|
Calving sign detection with cattle state-based feature extraction from video frames Ryosuke Hyodo, Saki Yasuda (Waseda Univ.), Susumu Saito (Waseda Univ./iflab, inc.), Yusuke Okimoto (Waseda Univ.), Teppei Nakano, Makoto Akabane (Waseda Univ./iflab, inc.), Tetsunori Kobayashi, Tetsuji Ogawa (Waseda Univ.) PRMU2018-90 |
Requirements that camera-based automatic calving sign detection should meet are established and a system satisfying thes... [more] |
PRMU2018-90 pp.79-84 |
PRMU |
2018-12-14 14:55 |
Miyagi |
|
Interior style estimation using deep learning techniques for product recommendation. Yusuke Yamaura, Yukihiro Tsuboshita (FX) PRMU2018-91 |
(To be available after the conference date) [more] |
PRMU2018-91 pp.85-90 |
PRMU |
2018-12-14 15:50 |
Miyagi |
|
Bayes Boundary Estimation Capability Assessment for Large Geometric Margin Minimum Classification Error Training Ikuhiro Nishiyama (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Osaki (Doshisha Univ.) PRMU2018-92 |
The recent, Large Geometric Margin Minimum Classification Error training has, based on the smoothness of its smooth clas... [more] |
PRMU2018-92 pp.91-96 |
PRMU |
2018-12-14 16:05 |
Miyagi |
|
Experimental Evaluation of Automatic Determination of Loss Smoothness for Minimum Classification Error Training Kazuma Kobayashi (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.) PRMU2018-93 |
(To be available after the conference date) [more] |
PRMU2018-93 pp.97-102 |
PRMU |
2018-12-14 16:20 |
Miyagi |
|
Correcting Outputs of Ensemble LSTMs by CRF for Robust Activity Recognition Haruka Abe, Yuta Hayakawa (Tokyo Tech), Takuya Hino, Motohide Sugihara, Hiroki Ikeya (KOMATSU), Masamichi Shimosaka (Tokyo Tech) PRMU2018-94 |
Recognizing the activities of the construction vehicle helps to assess the skill of the workers or give a technical guid... [more] |
PRMU2018-94 pp.103-108 |