ken-system: Advance Program

IEICE Technical Committee Submission System
Advance Program

Online Proceedings
[Sign in]
Tech. Rep. Archives

===============================================
Technical Committee on Pattern Recognition and Media Understanding (PRMU)
Chair: Seiichi Uchida (Kyushu Univ.)
Vice Chair: Masakazu Iwamura (Osaka Pref. Univ.), Mitsuru Anpai (Denso IT Lab.)
Secretary: Takashi Shibata (NTT), Masashi Nishiyama (Tottori Univ.)
Assistant: Kouta Yamaguchi (CyberAgent), Yusuke Matsui (Univ. of Tokyo)

DATE:
Thu, Dec 16, 2021 10:30 - 18:00
Fri, Dec 17, 2021 10:30 - 16:30

PLACE:

TOPICS:

----------------------------------------
Thu, Dec 16 AM (10:30 - 12:00)
----------------------------------------

(1) 10:30 - 10:45
Utilization of Synthetic Data for Mud Stain Removal from Single Image
Shusaku Asada, Yoshihito Kokubo (Aisin Corp.), Masaru Koide (MACNICA, Inc.), Kohei Yamamoto (Corpy&Co., Inc.), Yoshihisa Suetsugu (Aisin Corp.)

(2) 10:45 - 11:00
Shadow Reduction Based on LiDAR intensity
Shogo Sato, Yasuhiro Yao, Shingo Ando, Jun Shimamura (NTT)

(3) 11:00 - 11:15
Low-Resolution Iris Recognition with Image Super-Resolution for arbitrary magnification
Tsubasa Bora (UEC), Takahiro Toizumi, Yuho Shoji, Yuka Ogino, Masato Tsukada (NEC), Masatsugu Ichino (UEC)

----------------------------------------
Thu, Dec 16 AM (10:30 - 12:00)
----------------------------------------

(4) 10:30 - 10:45
Real-world Anomaly Detection by Integrating Long-Term and Short-Term Classifications
Yudai Watanabe, Makoto Okabe (Shizuoka Univ.), Yasunori Harada, Yasuhiko Naoji (Chubu Electric Power Co., Inc.)

(5) 10:45 - 11:00
Selective Inference for Multi-dimensional Multiple Change-Points
Ryota Sugiyama, Hiroki Toda (NIT), Vo Nguyen Le Duy (NIT/RIKEN), Yu Inatsu (NIT), Ichiro Takeuchi (NIT/RIKEN)

(6) 11:00 - 11:15
Anomaly Detection using PatchCore with Self-attention module
Yuki Takena (Shizuoka Univ.), Yoshiki Nota, Rinpei Mochizuki (Meidensya Corp.), Itaru Matsumura (Railway Technical Research Inst.), Gosuke Ohashi (Shizuoka Univ.)

(7) 11:15 - 11:30
A Dataset for Work Instruction Deviation Detection from Field Work Videos
Ryosuke Furuta (UTokyo), Motohiro Takagi (NTT), Yusuke Sugano, Yoichi Sato (UTokyo)

----- Break ( 90 min. ) -----

----------------------------------------
Thu, Dec 16 PM (13:30 - 14:30)
----------------------------------------

----- Break ( 15 min. ) -----

----------------------------------------
Thu, Dec 16 PM (14:45 - 16:20)
----------------------------------------

(8) 14:45 - 14:55
Unsupervised Logo Detection Using Adversarial Learning from Synthetic to Real Images
Rahul Kumar Jain (Ritsumeikan Univ.), Takahiro Sato, Taro Watasue, Tomohiro Nakagawa (tiwaki), Yutaro Iwamoto (Ritsumeikan Univ.), Xiang Ruan (tiwaki), Yen-Wei Chen (Ritsumeikan Univ.)

(9) 14:55 - 15:10
Fully automatic scoring of handwritten descriptive answers in Japanese language tests
Hung Tuan Nguyen, Cuong Tuan Nguyen (TUAT), Haruki Oka (UTokyo), Tsunenori Ishioka (The National Center for University Entrance Examinations), Masaki Nakagawa (TUAT)

(10) 15:10 - 15:25
Neural Network-based Local Feature Descriptors for Matching Excavated Mokkan Fragments of Various Sizes
Trung Tan Ngo, Hung Tuan Nguyen, Masaki Nakagawa (TUAT)

(11) 15:25 - 15:35
[Short Paper]
Evaluation of Time Series Causal Discovery Method Using Plant Simulator
Kazuki Koyama, Daigo Fujiwara, Keisuke Kiritoshi, Tomomi Okawachi, Tomonori Izumitani (NTT Communications), Keisuke Asahara, Shohei Shimizu (Shiga Univ.)

----------------------------------------
Thu, Dec 16 PM (14:45 - 16:15)
----------------------------------------

(12) 14:45 - 15:00
Estimating the Effects of Reducing Human Flow Using Interrupted Time Series Analysis
Kazuma Doi (ITF.), Masaki Onishi (AIST)

(13) 15:00 - 15:15
State Estimation Scheme of Input Work using Sight Information
Tatsuya Desaki, Daichi Ogo, Takahiro Koita (Doshisha Univ)

(14) 15:15 - 15:30
Multivariate time series forecasting accuracy improvement method based on LSTNet
Hayato Sano, Jun Rokui (Univ of Shizuoka)

----- Break ( 15 min. ) -----

----------------------------------------
Thu, Dec 16 PM (16:30 - 18:00)
----------------------------------------

(15) 16:30 - 16:45
Recurrent Tracknet : Continuous ball detection using Deep Neural Network
Gen Maesako, Toshikazu Wada (Wakayama Univ.)

(16) 16:45 - 17:00
Verification of Cyclical Annealing for Object-Oriented Representation Learning
Atsushi Kobayashi (Waseda Univ.), Hideki Tsunashima (Waseda Univ./AIST), Takehiko Ohkawa (The Univ. of Tokyo), Hiroaki Aizawa (Hiroshima Univ.), Qiu Yue, Hirokatsu Kataoka (AIST), Shigeo Morishima (Waseda Univ.)

(17) 17:00 - 17:15
Weakly Supervised Image Manipulation Detection with Class Activation Maps
Taisei Takahashi, Satoshi Iizuka, Kazuhiro Fukui (Tsukuba Univ)

----------------------------------------
Thu, Dec 16 PM (16:30 - 18:00)
----------------------------------------

(18) 16:30 - 16:45
Examination of facial pattern structure estimation using GCN
Naoya Maruoka, Toshikazu Wada (Wkayama Univ.)

(19) 16:45 - 17:00
Supervoxel-based Explanation for Action Recognition
Ying Ji (Nagoya Univ.), Yu Wang (Ritsumeikan Univ.), Kensaku Mori (Nagoya Univ.), Jien Kato (Ritsumeikan Univ.)

(20) 17:00 - 17:15
Evaluation of CNNs with Narrow Receptive Fields in Crowd Counting
Junya Uchida, Yu Wang, Jien Kato (Ritsumeikan Univ.)

----------------------------------------
Fri, Dec 17 AM (10:30 - 12:00)
----------------------------------------

(21) 10:30 - 10:45
Automatic estimation of sleep state by multi-view video analysis
Naoyuki Ebata, Shinya Fukumoto, Masayuki Kashima, Mutumi Watanabe, Hitoshi Sakimoto, Takanori Ishizuka, Masayuki Nakamura (Kagoshima Univ)

(22) 10:45 - 11:00
Analysis of Recognition Grounds of Models for Social Relationship Recognition Using Spatial-temporal TCAV
Runa Sugiyama (Ritsumeikan Univ.), Ying JI (Nagoya Univ.), Yu Wang, Jien Kato (Ritsumeikan Univ.)

(23) 11:00 - 11:15
(See Japanese page.)

(24) 11:15 - 11:30
Automatic Video Summarization Using Archive of Edited Videos
Haruna Watanabe, Soma Shiraishi, Jun Piao, Katsuhiko Takahashi (NEC), Yu Nabeto (NEC Solution Innovators)

----------------------------------------
Fri, Dec 17 AM (10:30 - 12:00)
----------------------------------------

(25) 10:30 - 10:45
Data Augmentation to Robust Deep Learning-Based Lesion Classification for CT Image with Different Imaging Conditions
Nobuhiro Miyazaki, Hiroaki Takebe, Takayuki Baba (FUJITSU), Hiroaki Terada, Toru Higaki, Kazuo Awai (Hiroshima Univ.), Masahiko Shimada (Fujitsu Japan)

(26) 10:45 - 11:00
Data augmentation for domain adaptation by class consistency using soft target
Wataru Imaeda (Kyocera Corp.), Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi (Chubu Univ.)

(27) 11:00 - 11:15
Object Detection with FIR Camera using Domain Adaptation
Yuzuru Nakamura, Yasunori Ishii, Satoshi Sato, Yuki Maruyama (Panasonic), Takayoshi Yamashita (Chubu University)

----- Break ( 90 min. ) -----

----------------------------------------
Fri, Dec 17 PM (13:30 - 14:30)
----------------------------------------

----- Break ( 15 min. ) -----

----------------------------------------
Fri, Dec 17 PM (14:45 - 16:30)
----------------------------------------

(28) 14:45 - 15:00
Data Selection for Efficient Deep Learning
Ryota Higashi, Toshikazu Wada (Wakayama Univ.)

(29) 15:00 - 15:15
Toward high-accuracy CNN learning using dropout.
Hirokazu Akiba, Toshikazu Wada (Wakayama Univ.)

(30) 15:15 - 15:30
An LSTM-based prefetcher exploiting delta correlation
Hiroki Taniai, Tomoki Nakamura, Toru Koizumi, Yuya Degawa, Hidetsugu Irie, Shuichi Sakai, Ryota Shioya (Tokyo Univ.)

(31) 15:30 - 15:40
[Short Paper]
The classification of cancer in Pathological image with easy annotation
Tatsuhiko Sugimoto (Kyushu Univ.), Kazuhiro Terada, Akihiko Yoshizawa (Kyoto Univ.), Ryoma Bise (Kyushu Univ.)

(32) 15:40 - 15:50
[Short Paper]
Segmentation of Cervical Cancer Pathological Image
Kengo Araki (Kyushu Univ.), Mariyo Rokutan-Kurata, Kazuhiro Terada, Akihiko Yoshizawa (Kyoto Univ.), Ryoma Bise (Kyushu Univ.)

----------------------------------------
Fri, Dec 17 PM (14:45 - 16:15)
----------------------------------------

(33) 14:45 - 15:00
(See Japanese page.)

(34) 15:00 - 15:15
Adaptive Information Presentation Based on Person State Recognition
Sota Morita, Shinya Fukumoto, Masayuki Kashima, Mutsumi Watanabe (Kagoshima Univ.)

(35) 15:15 - 15:30
Task-independent redundancy reduction method using regularization for efficient neural network training
Charvi Vitthal, Florian Beye, Koichi Nihei, Hayato Itsumi (NEC)

(36) 15:30 - 15:40
[Short Paper]
Prediction Model of Early Recurrence of Hepatocellular Carcinoma Based on Deep Learning with Attention Module
Weibin Wang (Ritsumeikan Univ.), Fang Wang, Qingqing Chen (Zhejiang Univ.), Yutaro Iwamoto (Ritsumeikan Univ.), Xianhua Han (Yamaguchi Univ.), Yen-wei Chen (Ritsumeikan Univ.)

# Information for speakers
General Talk will have 15 minutes for presentation.

=== Technical Committee on Pattern Recognition and Media Understanding (PRMU) ===
# FUTURE SCHEDULE:

Thu, Mar 10, 2022 - Fri, Mar 11, 2022: Online [Fri, Jan 14], Topics: Differentiable rendering

# SECRETARY:
Contact address: pr