Thu, Dec 17 AM
10:00 - 12:00 |
| (1) |
10:00-10:15 |
Inter-intra Contrastive Framework for Self-supervised Spatio-temporal Learning |
Li Tao, Xueting Wang, Toshihiko Yamasaki (UTokyo) |
| (2) |
10:15-10:30 |
Synthesize talking anime-heads images by tunneling through human-heads domain |
Shun Fujiuchi, Ryo Hachiuma, Kunihiro Hasegawa, Hideo Saito (Keio Univ.) |
| (3) |
10:30-10:45 |
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.) |
| (4) |
10:45-11:00 |
Simultaneous pose-region estimation for people tracking |
Kazuhiko Watanabe, Toshikazu Wada (Wakayama Univ.) |
| (5) |
11:00-11:15 |
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.) |
| (6) |
11:15-11:30 |
A Novel Data Augmentation Framework Based on SeqGAN for Sentiment Analysis |
Jiawei Luo, Mondher Bouazizi, Tomoaki Ohtsuki (Keio Univ.) |
| (7) |
11:30-12:00 |
|
| |
12:00-13:30 |
Break ( 90 min. ) |
Thu, Dec 17 PM
13:30 - 14:30 |
| (8) |
13:30-14:30 |
[Invited Talk]
TBA |
Kota Matsui (Nagoya Univ.) |
| |
14:30-14:40 |
Break ( 10 min. ) |
Thu, Dec 17 PM
14:40 - 16:10 |
| (9) |
14:40-14:55 |
Belonging Network
-- Few-shot One-class Image Classification for Classes with Various Distributions -- |
Takumi Ohkuma, Hideki Nakayama (UT) |
| (10) |
14:55-15:10 |
Improving the accuracy of unsupervised segmentation by introducing a Laplacian filter loss function
-- Application to automotive wire harness components -- |
Yuki Matsumoto (SEI) |
| (11) |
15:10-15:25 |
Hierarchical Contrastive Adaptation for Cross-Domain Object Detection |
Ziwei Deng, Quan Kong, Naoto Akira, Tomoaki Yoshinaga (Hitachi) |
| (12) |
15:25-15:40 |
Visual inspection system with a small number of anomalous data using DevNet |
Katsuhisa Kitaguchi, Yohei Nishizaki, Mamoru Saito (ORIST) |
| (13) |
15:40-16:10 |
|
| |
16:10-16:20 |
Break ( 10 min. ) |
Thu, Dec 17 PM
16:20 - 18:00 |
| (14) |
16:20-16:30 |
[Short Paper]
Few-Shot Incremental Learning by Unifying with Variational Autoencoder |
Keita Takayama, Kuniaki Uto, Koichi Shinoda (TokyoTech) |
| (15) |
16:30-16:45 |
Towards Discovery of Relevant Latent Factors with Limited Data |
Mohit Chhabra, Quan Kong, Tomoaki Yoshinaga (Hitachi) |
| (16) |
16:45-17:00 |
Vehicle detection using visualization of deep learning from in-vehicle night-time camera image |
Tatsuya Oyabu, Gosuke Ohashi (Shizuoka Univ.) |
| (17) |
17:00-17:15 |
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) |
| (18) |
17:15-17:30 |
Transfer learning from sparse models
-- Two approaches and optimization issues -- |
Tomoya Sakai, Rabi Yamada, Ryoji Ishibashi, Hiroyuki Takada (Nagasaki Univ.) |
| (19) |
17:30-18:00 |
|
Fri, Dec 18 AM
10:00 - 12:00 |
| (20) |
10:00-10:15 |
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) |
| (21) |
10:15-10:30 |
Corner point detection with reliability metric for homography warping of planer objects |
Hiroya Fujiura, Toshikazu Wada (Wakayama Univ) |
| (22) |
10:30-10:45 |
Pear Flower Cluster Detection Method Using Deep Learning and Branch Extraction |
Shunsuke Aoki, Tatsuya Yamazaki (Niigata Univ.) |
| (23) |
10:45-11:00 |
CNN and 2D BLSTM for Local Feature Extraction in Handwritten Mathematical Expression Recognition |
Kei Morizumi, Cuong Tuan Nguyen, Ikuko Shimizu, Masaki Nakagawa (TUAT) |
| (24) |
11:00-11:15 |
Depth image prediction of transparent objects based on image-to-image translation |
Ryo Iimori (KIT), Ryosuke Kubota, Kiyoshi Kogure (KIT) |
| (25) |
11:15-11:30 |
Supervised disentangled representation learning
-- Disentangling features using classifier -- |
Shujiro Kuroda, Toshikazu Wada (Wakayama Univ.) |
| (26) |
11:30-12:00 |
|
| |
12:00-13:15 |
Break ( 75 min. ) |
Fri, Dec 18 PM
13:15 - 14:15 |
| (27) |
13:15-14:15 |
[Invited Talk]
TBA |
Youichi Nonaka (Hitachi) |
| |
14:15-14:25 |
Break ( 10 min. ) |
Fri, Dec 18 PM
14:25 - 16:10 |
| (28) |
14:25-14:40 |
Zero-shot generative model considering attribute uncertainty |
Yuta Sakai (Waseda Univ.), Kenta Mikawa (SIT), Masayuki Goto (Waseda Univ.) |
| (29) |
14:40-14:55 |
Construction of SSD model applied Feature Contraction and Rand Augment by small training data |
Tomokazu Ozawa (UNICO), Yuki Matsumoto, Katsushi Miura (SEI), Takuya Okuno (SCE) |
| (30) |
14:55-15:10 |
Regularization Using Knowledge Distillation in Learning Small Datasets |
Ryota Higashi, Toshikazu Wada (Wakayama Univ.) |
| (31) |
15:10-15:25 |
A Hybrid Sampling Strategy for Improving the Accuracy of Image Classification with less Data |
Ruiyun Zhu, Fumihiko Ino (Osaka Univ.) |
| (32) |
15:25-15:40 |
Multi-Task Attention Learning for Fine-grained Recognition |
Dichao Liu (NU), Yu Wang (Rits), Kenji Mase (NU), Jien Kato (Rits) |
| (33) |
15:40-16:10 |
|
| |
16:10-16:20 |
Break ( 10 min. ) |
Fri, Dec 18 PM
16:20 - 18:00 |
| (34) |
16:20-16:30 |
[Short Paper]
Case Discrimination: Self-supervised Learning for classification of Medical Image |
Haohua Dong, Yutaro Iwamoto (Ritsumeikan Univ.), Xianhua Han (Yamaguchi Univ.), Lanfen Lin (Zhejiang Univ.), Hongjie Hu, Xiujun Cai (Sir Run Run Shaw Hospital), Yen-Wei Chen (Ritsumeikan Univ.) |
| (35) |
16:30-16:45 |
Estimating 3D regions for grasping an object |
Atsuki Tsukamoto, Kiyoshi Kogure (KIT) |
| (36) |
16:45-17:00 |
|
Shohei Kubota, Hideaki Hayashi (Kyushu Univ.), Tomohiro Hayase (Fujitsu Lab.), Seiichi Uchida (Kyushu Univ.) |
| (37) |
17:00-17:15 |
An evaluation method of area detection AI based on contribution pattern variation with noise addition |
Yasuhide Mori, Naofumi Hama, Masashi Egi (Hitachi) |
| (38) |
17:15-17:30 |
Rethinking the local similarity in content-based image retrieval |
Longjiao Zhao (Nagoya Univ.), Yu Wang (Ritsumeikan Univ), Yoshiharu Ishikawa (Nagoya Univ.), Jien Kato (Ritsumeikan Univ) |
| (39) |
17:30-18:00 |
|
-or
zer
