Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU, IPSJ-CVIM |
2021-03-04 09:30 |
Online |
Online |
Automatic 3D Mesh Generation by Using Extended Attentive Normalization Yuta Fukatsu, Masaki Aono (TUT) PRMU2020-69 |
In recent years, research on conditional image generation using GANs of the type where conditions are given by class lab... [more] |
PRMU2020-69 pp.1-6 |
PRMU, IPSJ-CVIM |
2021-03-04 09:45 |
Online |
Online |
Discrimination between Real and Cloned Images by Ensemble Learning of GAN Discriminators Naoki Hamasaki, Kazuaki Nakamura, Naoko Nitta, Noboru Babaguchi (Osaka Univ.) PRMU2020-70 |
(To be available after the conference date) [more] |
PRMU2020-70 pp.7-12 |
PRMU, IPSJ-CVIM |
2021-03-04 10:00 |
Online |
Online |
Saliency Detection by Extended Attention and its Application to Image Synthesis Ryosuke Yamauchi, Masaki Aono (TUT) PRMU2020-71 |
In recent years, there has been much research on Style Transfer and Saliency Detection.
Style Transfer is a task to sy... [more] |
PRMU2020-71 pp.13-18 |
PRMU, IPSJ-CVIM |
2021-03-04 10:15 |
Online |
Online |
Semi-supervised temporal image sequence generation conditioned on non-visual sensor signals Kawakami Sota, Kei Okada, Naoko Nitta, Kazuaki Nakamura, Noboru Babaguchi (Osaka Univ.) PRMU2020-72 |
(To be available after the conference date) [more] |
PRMU2020-72 pp.19-24 |
PRMU, IPSJ-CVIM |
2021-03-04 10:30 |
Online |
Online |
Learning Convolutional Neural Networks with Spatial Frequency Loss Naoyuki Ichimura (AIST) PRMU2020-73 |
The pixel-wise L2 and pixel-wise L1 losses have been commonly used to measure the consistency between images in learning... [more] |
PRMU2020-73 pp.25-30 |
PRMU, IPSJ-CVIM |
2021-03-04 10:45 |
Online |
Online |
[Short Paper]
High-Resolution Image Completion by Hierarchical Neural Process Masato Miyahara, Daisuke Sato, Masato Fukuda, Narimune Matsumura, Yoshiki Nishikawa (NTT) PRMU2020-74 |
Neural Process (NP) is a deep generation model which can consider the uncertainty of prediction.
The unknown output is ... [more] |
PRMU2020-74 pp.31-34 |
PRMU, IPSJ-CVIM |
2021-03-04 13:00 |
Online |
Online |
[Fellow Memorial Lecture]
Interdisciplinary Sociological and Engineering Research on Human-Robot Interaction Yoshinori Kuno (Saitama Univ.) |
This talk presents an overview of our interdisciplinary sociological and engineering research on human-robot interaction... [more] |
|
PRMU, IPSJ-CVIM |
2021-03-04 14:10 |
Online |
Online |
multi-modal action recognition system
-- recognizing actions based on RGB video, skeleton, audio and text data -- Hang Yuan, Taichi Imura, Misaki Fujishiro, Takashi Suenaga, Kengo Makino, Yuto Yamanoue (NTT Data) PRMU2020-75 |
[more] |
PRMU2020-75 pp.35-40 |
PRMU, IPSJ-CVIM |
2021-03-04 14:25 |
Online |
Online |
Leveraging Human Pose Estimation Model for Sports Video Classification Soichiro Sato, Masaki Aono (TUT) PRMU2020-76 |
In this paper, we propose a motion classification method of sports videos based on a posture estimation model.Specifical... [more] |
PRMU2020-76 pp.41-46 |
PRMU, IPSJ-CVIM |
2021-03-04 14:40 |
Online |
Online |
Evaluations on Two-stream Feature-fusion Architecture with Shifting-subclip and Hard Positive Mining for Person Re-identification Yuki Hiroi, Wataru Kameyama (Waseda Univ.) PRMU2020-77 |
As a person re-identification technology using spatial-temporal features (video-based Re-ID), we have proposed two-strea... [more] |
PRMU2020-77 pp.47-52 |
PRMU, IPSJ-CVIM |
2021-03-04 14:55 |
Online |
Online |
Word-level sign language recognition with Multi-stream Neural Networks Focusing on Local Region Mizuki Maruyama (Osaka Pref. Univ.), Shuvozit Ghose (IIT), Katsufumi Inoue (Osaka Pref. Univ.), Partha Pratim Roy (IIT), Masakazu Iwamura, Michifumi Yoshioka (Osaka Pref. Univ.) PRMU2020-78 |
(To be available after the conference date) [more] |
PRMU2020-78 pp.53-58 |
PRMU, IPSJ-CVIM |
2021-03-04 15:50 |
Online |
Online |
Automated Segmentation of Left Ventirular Wall and Extraction of Left Ventricular Cavity in Echocardiographic Images by Deep Learning Kai Wang, JiWei Zhang (Wakayama Univ.), Takeshi Hozumi (Wakayama Medical Univ.), HaiYuan Wu (Wakayama Univ.) PRMU2020-79 |
In order to interpret cardiac function using echocardiographic images, it requires a great deal of skill. To construct o... [more] |
PRMU2020-79 pp.59-64 |
PRMU, IPSJ-CVIM |
2021-03-04 16:05 |
Online |
Online |
Media detection from cardiovascular OCT images based on deep learning jiwei zhang, kai wang (wakayama univ), Takashi Kubo (Wakayama Medical Univ), haiyuan wu (wakayama univ) PRMU2020-80 |
Medical image segmentation is an important issue in determining whether medical images can provide reliable evidence in ... [more] |
PRMU2020-80 pp.65-70 |
PRMU, IPSJ-CVIM |
2021-03-04 16:20 |
Online |
Online |
VQA for Medical Image Data based on Image Feature Extraction and Fusion Hideo Umada, Masaki Aono (TUT) PRMU2020-81 |
In recent years, there has been a remarkable growth in research on deep learning in the fields of computer vision and na... [more] |
PRMU2020-81 pp.71-76 |
PRMU, IPSJ-CVIM |
2021-03-04 16:35 |
Online |
Online |
Quantifying detection quality in the presence of adversarial inputs in dermatological images Mishra Sourav (UTokyo), Hideaki Imaizumi (exMedio), Toshihiko Yamasaki (UTokyo) PRMU2020-82 |
We have tested deep learning based detection on dermatological conditions commonly encountered in clinical settings. Des... [more] |
PRMU2020-82 pp.77-82 |
PRMU, IPSJ-CVIM |
2021-03-04 16:50 |
Online |
Online |
[Short Paper]
A CNN-Transformer-Based Network for Depression Recognition Liu Jiaqing (Ritsumei), Huang Yue, Huang Xinren (Soochow), Tateyama Tomoko (Shiga University), Iwamoto Yutaro, Chen Yanwei (Ritsumei) PRMU2020-83 |
Depressive symptoms are a massive problem in this stressful modern society. Early screening of depressive symptoms helps... [more] |
PRMU2020-83 pp.83-85 |
PRMU, IPSJ-CVIM |
2021-03-05 09:30 |
Online |
Online |
A discussion on live sampling techniques for sound materials in media art Yoichi Nagashima (SUAC) PRMU2020-84 |
In media art, such as live computer music performances and interactive installations, it's been about 20 years becoming ... [more] |
PRMU2020-84 pp.86-90 |
PRMU, IPSJ-CVIM |
2021-03-05 09:45 |
Online |
Online |
Improved Speech Separation Performance from Monaural Mixed Speech Based on Deep Embedding Network Shaoxiang Dang, Tetsuya Matsumoto, Hiroaki Kudo (Nagoya Univ.), Yoshinori Takeuchi (Daido Univ.) PRMU2020-85 |
Speech separation refers to the separation of utterances in which multiple people are speaking simultaneously. The idea ... [more] |
PRMU2020-85 pp.91-96 |
PRMU, IPSJ-CVIM |
2021-03-05 10:00 |
Online |
Online |
Automatic music transcription system based on convolutional neural network for electric guitar considering sounds of same pitch and different strings Toshiaki Matsui, Tetsuya Matsumoto, Hiroaki Kudo (Nagoya Univ), Yoshinori Takeuchi (Daido Univ) PRMU2020-86 |
In this research, we propose a system that outputs tablature notation of an electric guitar performance from acoustic si... [more] |
PRMU2020-86 pp.97-102 |
PRMU, IPSJ-CVIM |
2021-03-05 10:15 |
Online |
Online |
Counting Fruits and Flowers by Using Object Detection with Time-Lapse Camera Images Akihiro Tanikawa, Yuma Usui, Takaya Matsumoto (KUT/Office asoT), Mitsuhiro Osaki, Kazuma Nishiuchi (Citynet), Masahiro Fukumoto (KUT) PRMU2020-87 |
It is important issues to optimize cultivation/production control and prediction of harvest time for improving agricultu... [more] |
PRMU2020-87 pp.103-108 |