| IEICE Technical Committee Submission System Conference Schedule |
Online Proceedings [Sign in] Tech. Rep. Archives |
Technical Committee on Pattern Recognition and Media Understanding (PRMU) (Searched in: 2020)
Search Results: Keywords 'from:2020-12-17 to:2020-12-17'
| Committee | Date Time | Place | Paper Title / Authors | Abstract | Paper # | |
| PRMU | 2020-12-17 10:00 |
Online | Online | Inter-intra Contrastive Framework for Self-supervised Spatio-temporal Learning Li Tao, Xueting Wang, Toshihiko Yamasaki (UTokyo)  PRMU2020-38 |
[more] | PRMU2020-38 pp.1-6 |
| PRMU | 2020-12-17 10:15 |
Online | Online | Synthesize talking anime-heads images by tunneling through human-heads domain Shun Fujiuchi, Ryo Hachiuma, Kunihiro Hasegawa, Hideo Saito (Keio Univ.) PRMU2020-39 |
Avatars are widely used on the Internet to establish non-verbal communication without exposing one's physical identity. ... [more] | PRMU2020-39 pp.7-11 |
| PRMU | 2020-12-17 10:30 |
Online | Online | Simultaneous learning of object foreground, pose and class using only class teacher Shunsuke Yoneda (Tottori Univ.), Go Irie (NTT), Masashi Nisiyama, Yoshio Iwai (Tottori Univ.) PRMU2020-40 |
(To be available after the conference date) [more] | PRMU2020-40 pp.12-17 |
| PRMU | 2020-12-17 10:45 |
Online | Online | Simultaneous pose-region estimation for people tracking Kazuhiko Watanabe, Toshikazu Wada (Wakayama Univ.) PRMU2020-41 |
Bottom-up pose estimation often make an incorrect connection between body parts in a crowded situation like group photo.... [more] | PRMU2020-41 pp.18-23 |
| PRMU | 2020-12-17 11:00 |
Online | Online | Fast algorithm for low-rank tensor completion in multi-way delay embedded space Ryuki Yamamoto, Tatsuya Yokota (Nagoya Institute of Tech.), Akira Imakura (Univ. of Tsukuba), Hidekata Hontani (Nagoya Institute of Tech.) PRMU2020-42 |
In recent years, low-rank tensor completion using delay embedding has been an important technique. In order to capture s... [more] | PRMU2020-42 pp.24-29 |
| PRMU | 2020-12-17 11:15 |
Online | Online | A Novel Data Augmentation Framework Based on SeqGAN for Sentiment Analysis Jiawei Luo, Mondher Bouazizi, Tomoaki Ohtsuki (Keio Univ.) PRMU2020-43 |
Sentiment analysis is an important field in Natural Language Processing (NLP). It can analyze people's sentiment through... [more] | PRMU2020-43 pp.30-35 |
| PRMU | 2020-12-17 13:30 |
Online | Online | [Invited Talk]
TBA Kota Matsui (Nagoya Univ.) |
[more] | |
| PRMU | 2020-12-17 14:40 |
Online | Online | Belonging Network
-- Few-shot One-class Image Classification for Classes with Various Distributions -- Takumi Ohkuma, Hideki Nakayama (UT) PRMU2020-44 |
Few-shot one-class image classification is the task of recognizing a particular class while rejecting test images that d... [more] | PRMU2020-44 pp.36-41 |
| PRMU | 2020-12-17 14:55 |
Online | Online | Improving the accuracy of unsupervised segmentation by introducing a Laplacian filter loss function
-- Application to automotive wire harness components -- Yuki Matsumoto (SEI) PRMU2020-45 |
Semantic segmentation, in which images are classified into pixel-by-pixel classes by deep learning, has been widely stud... [more] | PRMU2020-45 pp.42-46 |
| PRMU | 2020-12-17 15:10 |
Online | Online | Hierarchical Contrastive Adaptation for Cross-Domain Object Detection Ziwei Deng, Quan Kong, Naoto Akira, Tomoaki Yoshinaga (Hitachi) PRMU2020-46 |
Object detection based on deep learning has been enormously developed in recent years. However, applying detectors train... [more] | PRMU2020-46 pp.47-52 |
| PRMU | 2020-12-17 15:25 |
Online | Online | Visual inspection system with a small number of anomalous data using DevNet Katsuhisa Kitaguchi, Yohei Nishizaki, Mamoru Saito (ORIST) PRMU2020-47 |
A good visual inspection using deep learning needs to collect a large amount of anomalous data. To solve this problem, w... [more] | PRMU2020-47 pp.53-57 |
| PRMU | 2020-12-17 16:20 |
Online | Online | [Short Paper]
Few-Shot Incremental Learning by Unifying with Variational Autoencoder Keita Takayama, Kuniaki Uto, Koichi Shinoda (TokyoTech) PRMU2020-48 |
We propose a few-shot incremental learning method using a variational autoencoder for deep learning. In incremental lear... [more] | PRMU2020-48 pp.58-62 |
| PRMU | 2020-12-17 16:30 |
Online | Online | Towards Discovery of Relevant Latent Factors with Limited Data Mohit Chhabra, Quan Kong, Tomoaki Yoshinaga (Hitachi) PRMU2020-49 |
The remarkable effectiveness of neural networks on vision tasks has led to an interest in adapting neural network models... [more] | PRMU2020-49 pp.63-68 |
| PRMU | 2020-12-17 16:45 |
Online | Online | Vehicle detection using visualization of deep learning from in-vehicle night-time camera image Tatsuya Oyabu, Gosuke Ohashi (Shizuoka Univ.) PRMU2020-50 |
We have been working on vehicle detection at night-time using deep learning. In general, the burden of creating correct ... [more] | PRMU2020-50 pp.69-74 |
| PRMU | 2020-12-17 17:00 |
Online | Online | Learning Method for Ambiguous Lesion Boundaries in Endoscopy Images Yuta Kochi (Univ. of Tsukuba/AIST), Hirokazu Nosato (AIST), Atsushi Ikeda (Univ. of Tsukuba Hosp.), Hidenori Sakanashi (AIST) PRMU2020-51 |
(To be available after the conference date) [more] | PRMU2020-51 pp.75-79 |
| PRMU | 2020-12-17 17:15 |
Online | Online | Transfer learning from sparse models
-- Two approaches and optimization issues -- Tomoya Sakai, Rabi Yamada, Ryoji Ishibashi, Hiroyuki Takada (Nagasaki Univ.) PRMU2020-52 |
[more] | PRMU2020-52 pp.80-85 |
| PRMU | 2020-12-18 10:00 |
Online | Online | Report on MIRU 2020 Young Researchers Program Yuzuko Utsumi (OPU), Takafumi Iwaguchi (Kyushu Univ.), Xueting Wang (Univ. of Tokyo), Masanori Suganuma (Tohoku Univ./RIKEN), Mai Nishimura (Kyoto Univ./OSX), Kensho Hara (AIST), Tsubasa Hirakawa (Chubu Univ.), Hiroshi Fukui (NEC) PRMU2020-53 |
(To be available after the conference date) [more] | PRMU2020-53 pp.86-92 |
| PRMU | 2020-12-18 10:15 |
Online | Online | Corner point detection with reliability metric for homography warping of planer objects Hiroya Fujiura, Toshikazu Wada (Wakayama Univ) PRMU2020-54 |
When classifying flat and rectangle objects, such as product packages on shelves, from a slanted image taken at an angle... [more] | PRMU2020-54 pp.93-98 |
| PRMU | 2020-12-18 10:30 |
Online | Online | Pear Flower Cluster Detection Method Using Deep Learning and Branch Extraction Shunsuke Aoki, Tatsuya Yamazaki (Niigata Univ.) PRMU2020-55 |
Currently, manual pollination work in pear cultivation is a heavy burden for farmers, since a kind of pear has self-inco... [more] | PRMU2020-55 pp.99-104 |
| PRMU | 2020-12-18 10:45 |
Online | Online | CNN and 2D BLSTM for Local Feature Extraction in Handwritten Mathematical Expression Recognition Kei Morizumi, Cuong Tuan Nguyen, Ikuko Shimizu, Masaki Nakagawa (TUAT) PRMU2020-56 |
Descriptive questions in mathematics are effective to examine learners’ understanding, but marking handwritten answers a... [more] | PRMU2020-56 pp.105-110 |
[Return to Top Page]