Online edition: ISSN 2432-6380
[TOP] | [2018] | [2019] | [2020] | [2021] | [2022] | [2023] | [2024] | [Japanese] / [English]
PRMU2021-60
Deep Cascade Road Extraction Network: a Multi-task Method for Road Extraction
Yubo Wang (Waseda Univ.), Zhao Wang, Yuusuke Nakano, Ken Nishimatsu (NTT), Katsuya Hasegawa (JAXA), Jun Ohya (Waseda Univ.)
pp. 1 - 6
PRMU2021-61
Unsupervised adaptation of appearance-based gaze estimation models for domains with different label distributions.
Takuru Shimoyama, Yusuke Sugano (The Univ. of Tokyo)
pp. 7 - 12
PRMU2021-62
(See Japanese page.)
pp. 13 - 18
PRMU2021-63
(See Japanese page.)
pp. 19 - 24
PRMU2021-64
Medical Image Captioning with Information based on Medical Concepts
Riku Tsuneda, Tetsuya Asakawa (TUT), Kazuki Shimizu, Takuyuki Komoda (THC), Masaki Aono (TUT)
pp. 25 - 30
PRMU2021-65
Few-shot fine-grained image recognition by transfer-leaning using knowledge graph
Ryusei Taniguchi, Naoko Nitta (Osaka Univ.), Kazuaki Nakamura (TUS), Noboru babaguchi (Osaka Univ.)
pp. 31 - 36
PRMU2021-66
Designing tasks in meta-learning for few-shot fine-grained image recognition
Shunya Inoue, Naoko Nitta (Osaka Univ.), Kazuaki Nakamura (TUS), Noboru Babaguchi (Osaka Univ.)
pp. 37 - 41
PRMU2021-67
(See Japanese page.)
pp. 42 - 47
PRMU2021-68
(See Japanese page.)
pp. 48 - 53
PRMU2021-69
Visual Constraints for Generating Multi-domain Offline Handwritten Mathematical Expressions
Huy Quang Ung, Hung Tuan Nguyen, Cuong Tuan Nguyen (Tokyo Univ. Agri. & Tech.), Tsunenori Ishioka (The National Cen. for Univ. Entrance Exam.), Masaki Nakagawa (Tokyo Univ. Agri. & Tech.)
pp. 54 - 59
PRMU2021-70
Learning from AI: Proposal of interactive learning methods for learners learning from DNN embedded expertise knowledge as a teacher
Kohei Hattori, Hironobu Fujiyoshi, Takayoshi Yamashita, Tsubasa Hirakawa (CHUBU)
pp. 60 - 65
PRMU2021-71
Landslide detection by UAV-based Multi-temporal Visual Analysis
Yosuke Yamaguchi, Kai Matsui, Jun Ohya (Waseda Univ.), Katsuya Hasegawa (JAXA), Hiroshi Nagahashi (Tokyo Institute of Technology)
pp. 66 - 71
PRMU2021-72
Uncertainty-Aware Interactive LiDAR Sampling for Deep Depth Completion
Kensuke Taguchi, Shogo Morita, Yusuke Hayashi, Wataru Imaeda (KYOCERA), Hironobu Fujiyoshi (Chubu Univ)
pp. 72 - 77
PRMU2021-73
Adversarial Training: A Survey
Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi (Chubu Univ.)
pp. 78 - 90
PRMU2021-74
A Study on Understanding the Meaning of Adverbs by Frequency Spectrum Analysis Using Gaussian Process
Tomoe Taniguchi (Ochanomizu Univ.), Daichi Mochihashi (ISM), Masatoshi Nagano, Tomoaki Nakamura (UEC), Takayuki Nagai (Osaka Univ.), Tetsunari Inamura (NII), Ichiro Kobayashi (Ochanomizu Univ.)
pp. 91 - 96
PRMU2021-75
Generation of Handwritten Document Clones based on Font Style Transfer for Digital Document Images
Koma Sasaki (Osaka Univ.), Kazuaki Nakamura (Tokyo Univ. of Science of), Naoko Nitta, Noboru Babaguchi (Osaka Univ.)
pp. 97 - 102
PRMU2021-76
Context free grammar with tree structure analysis for online handwritten mathematical expression recognition
Naruki Kitashima, Cuong Tuan Nguyen, Ikuko Shimizu, Masaki Nakagawa (TUAT)
pp. 103 - 108
PRMU2021-77
Generation of Handwritten Character Clones based on Collaborative Filtering with Character-wise Feature Spaces
Koki Tamatani (Osaka Univ.), Kazuaki Nakamura (TUS), Naoko Nitta, Noboru Babaguchi (Osaka Univ.)
pp. 109 - 114
PRMU2021-78
Self-supervised Contrastive Learning Using Triplet Loss for Offline Recognition of Handwritten Chinese Text lines
Trung Tan Ngo, Hung Tuan Nguyen, Masaki Nakagawa (TUAT)
pp. 115 - 120
PRMU2021-79
Toward "Virtually" 100%; Quality Assurance Framework for Document Recognition
Hiroshi Tanaka (Fujitsu)
pp. 121 - 126
PRMU2021-80
Identifying a Person Wearing a Surgical Gown from Video Images Using Skeletal Information and Deep Learning
Shuhei Fujii (Waseda Univ.), Hiroshi Nagahashi (Tokyo Tech), Ken Masamune (Tokyo Women's Medical Univ.), Jun Ohya (Waseda Univ.)
pp. 127 - 132
PRMU2021-81
Precise Affordance Annotation for Egocentric Action Video Datasets
Zecheng Yu, Yifei Huang, Ryosuke Furuta, Yusuke Goutsu, Yoichi Sato (Univ. of Tokyo)
pp. 133 - 138
PRMU2021-82
Background Mixup Data Augmentation for Hand and Object-in-Contact Detection
Koya Tango, Takehiko Ohkawa, Ryosuke Furuta, Yoichi Sato (UTokyo)
pp. 139 - 144
PRMU2021-83
Hand Segmentation in Egocentric Videos by Combining UMA and MCD
Kenichi Suzuki, Katsufumi Inoue, Michifumi Yoshioka (Osaka Prefecture Univ.)
pp. 145 - 150
PRMU2021-84
(See Japanese page.)
pp. 151 - 156
PRMU2021-85
(See Japanese page.)
pp. 157 - 162
PRMU2021-86
Spatial attention and parallel convolution for Real-time segmentation
Yuki Sugimoto, Masaki Aono (TUT)
pp. 163 - 168
PRMU2021-87
(See Japanese page.)
pp. 169 - 174
PRMU2021-88
Extended Panel Detection and Pixel-Wise Segmentation for Comic Editing
Runtian Yu, Hikaru Ikuta, Yusuke Matsui, Kiyoharu Aizawa (UTokyo)
pp. 175 - 179
PRMU2021-89
(See Japanese page.)
pp. 180 - 185
PRMU2021-90
(See Japanese page.)
pp. 186 - 191
Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.