IEICE Technical Committee Submission System
Advance Program
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top  Go Back   / [HTML] / [HTML(simple)] / [TEXT]  [Japanese] / [English] 

===============================================
Technical Committee on Pattern Recognition and Media Understanding (PRMU)
Chair: Yoichi Sato (Univ. of Tokyo) Vice Chair: Toru Tamaki (Hiroshima Univ.), Akisato Kimura (NTT)
Secretary: Go Irie (NTT), Yoshitaka Ushiku (OMRON SINICX)
Assistant: Yusuke Uchida (DeNA), Takayoshi Yamashita (Chubu Univ.)

===============================================
Special Interest Group on Computer Vision and Image Media (IPSJ-CVIM)


DATE:
Mon, Mar 16, 2020 10:30 - 17:40
Tue, Mar 17, 2020 09:30 - 18:00

PLACE:
(075-753-5883)

TOPICS:


----------------------------------------
Mon, Mar 16 AM (10:30 - 11:50)
----------------------------------------

(1)/PRMU 10:30 - 10:45
A Hybrid of Discriminative and Generative Neural Networks
Hideaki Hayashi, Seiichi Uchida (Kyushu Univ.)

(2)/PRMU 10:45 - 11:00
Font analysis
Daichi Haraguchi, Shota Harada, Brian Kenji Iwana, Seiichi Uchida (Kyushu Univ.)

(3)/PRMU 11:00 - 11:10
[Short Paper]
Few-shot Character Image Generation with Deep Metric Learning
Haruka Aoki, Koki Tsubota, Hikaru Ikuta, Kiyoharu Aizawa (Tokyo Univ.)

(4)/PRMU 11:10 - 11:20
[Short Paper]
Video Inpainting by Frame Alignment with Deformable Convolution
Yusuke Hara, Xueting Wang, Toshihiko Yamasaki, Kiyoharu Aizawa (UTokyo)

(5) 11:20 - 11:50


----------------------------------------
Mon, Mar 16 AM (10:30 - 12:00)
----------------------------------------

(6)/PRMU 10:30 - 10:45
A Basic Study on Epipolar Geometry-based Ego-localization under Variable Illumination Conditions using a Far Infrared Camera
Haruya Kyutoku, Tokihiko Akita, Seiichi Mita (Toyota Tech. Inst.)

(7)/PRMU 10:45 - 11:00
Moment-Sentence Grounding from Temporal Action Proposal
Nao Yamada, Masaki Hayashi, Seito Kasai, Yoshimitsu Aoki (Keio Univ.)

(8)/PRMU 11:00 - 11:15
Multimodal Recipe Search and Image Generation by Disentangling Contents and Styles
Yu Sugiyama, Keiji Yanai (UEC)

(9)/PRMU 11:15 - 11:30
Image Synthesis Based on Style Features and Mask Images Using a Ramen Style Encoder
Jaehyeong Cho, Wataru Shimoda, Keiji Yanai (UEC)

(10) 11:30 - 12:00


----- Break -----

----------------------------------------
Mon, Mar 16 PM (13:30 - 14:30)
----------------------------------------

(11) 13:30 - 14:30


----- Break -----

----------------------------------------
Mon, Mar 16 PM (14:40 - 16:00)
----------------------------------------

(12)/PRMU 14:40 - 14:55
Egocentric pedestrian motion prediction by separately modeling body pose and position
Donghao Wu, Takuma Yagi, Yusuke Matsui, Yoichi Sato (the Univ. of Tokyo)

(13)/PRMU 14:55 - 15:10
Egocentric Action Recognition on Noisy Videos
Lijin Yang, Yifei Huang, Yusuke Sugano, Yoichi Sato (UTokyo)

(14)/PRMU 15:10 - 15:20
[Short Paper]
Feature Point Matching by Cycle Consistency
Naoaki Noguchi, Furuta Ryosuke, Xueting Wang, Toshihiko Yamasaki, Kiyoharu Aizawa (UT)

(15)/PRMU 15:20 - 15:35
Investigation of Real-Time 3D Head Position Estimation for Gesture Interface for People with Motor Dysfunction
Yuki Ozawa (Tsukuba Univ./AIST), Ikushi Yoda (AIST)

(16) 15:35 - 16:00


----------------------------------------
Mon, Mar 16 PM (14:40 - 16:05)
----------------------------------------

(17)/PRMU 14:40 - 14:55
Projector Calibration using a Pinhole Mask Plate
Masatoki Sugimoto, Daisuke Iwai, Kosuke Sato (Osaka Univ.)

(18)/PRMU 14:55 - 15:10
Joint Estimation of Illumination Distribution and Response Function from Shadows
Takuto Nakashima, Ryo Matsuoka, Takahiro Okabe (Kyutech)

(19)/PRMU 15:10 - 15:25
Metal Material Analysis using SEM Images of Multiple Magnifications
Ryunosuke Ito, Keisuke Kameyama (Univ. Tsukuba), Hideitsu Hino (ISM)

(20)/PRMU 15:25 - 15:40
Assessing robustness of deep learning methods in dermoscopic workflow
Sourav Mishra (Univ. of Tokyo), Hideaki Imaizumi (exMedio), Toshihiko Yamasaki (Univ. of Tokyo)

(21) 15:40 - 16:05


----- Break -----

----------------------------------------
Mon, Mar 16 PM (16:20 - 17:40)
----------------------------------------

(22)/PRMU 16:20 - 16:35
Transforming Simulation Images to Real Scene Images and Planning Driving Routes by Deep Learning for Achieving Automatic Car Driving
Zhang Zelin, Jun Ohya (Waseda Univ.)

(23)/PRMU 16:35 - 16:45
[Short Paper]
Correspondence of 360 degree video with distorted floor map and provision of 3D information
Jack Chen, Naoki Sugimoto, Satoshi Ikehata, Kiyoharu Aizawa (Tokyo Univ.)

(24)/PRMU 16:45 - 17:00
(See Japanese page.)

(25)/PRMU 17:00 - 17:15
Fine-grained Image Recognition using Geo-spatial Concept Knowledge Graphs with Graph Convolutional Networks
Yuki Shigyo, Naoko Nitta, Kazuaki Nakamura, Noboru Babaguchi (Osaka Univ.)

(26) 17:15 - 17:40


----------------------------------------
Mon, Mar 16 PM (16:20 - 17:40)
----------------------------------------

(27)/PRMU 16:20 - 16:30
[Short Paper]
Aleatoric Uncertainty Estimation Based on Separate Formulation
Takumi Kawashima, Qing Yu (Tokyo Univ.), Akari Asai (.UW), Daiki Ikami (NTT/Tokyo Univ.), Kiyoharu Aizawa (Tokyo Univ.)

(28)/PRMU 16:30 - 16:45
Faster Approximate Nearest Neighbor Search using Label Information of Images
Onur Guler, Yusuke Matsui, Yoichi Sato (UTokyo)

(29)/PRMU 16:45 - 17:00
Image compression by colorization
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Tatsuaki Hashimoto (UTokyo)

(30)/PRMU 17:00 - 17:15
Continuous Variables Estimation Through Classification Networks Ensembles
Qianyuan Liu (Nagoya Univ.), Yu Wang, Jien Kato (Ritsumeikan Univ.)

(31) 17:15 - 17:40


----------------------------------------
Tue, Mar 17 AM (09:30 - 10:20)
----------------------------------------

(32)/PRMU 09:30 - 09:45
Object area extraction with biased training data set
Ryo Nakamura, Yoshiaki Ueda, Jun Fujiki, Masaru Tanaka (Fukuoka Univ)

(33)/PRMU 09:45 - 10:00
Rule Extraction from convolutional neural networks
-- Rule Extraction with A Pedagogical Method --
Yuya Sato (Tokyo Denki Univ), Hiroshi Tsukimoto (Tokyo Denki Univ.)

(34) 10:00 - 10:20


----------------------------------------
Tue, Mar 17 AM (09:30 - 10:20)
----------------------------------------

(35)/PRMU 09:30 - 09:45
Evaluation of Initial Value of Nelder-Mead Method in Hyperparameter Optimization of Deep Learning
Shintaro Takenaga (Kindai Univ), Shuhei Watanabe, Masahiro Nomura, Yoshihiko Ozaki, Masaki Onishi (AIST), Hitoshi Habe (Kindai Univ)

(36)/PRMU 09:45 - 10:00
Deep neural network representation and learning of low-rank and sparse approximation
-- With application to celiac angiography under free breathing --
Ryohei Miyoshi, Tomoya Sakai (Nagasaki Univ.), Takashi Ohnishi, Hideaki Haneishi (Chiba Univ.)

(37) 10:00 - 10:20


----- Break -----

----------------------------------------
Tue, Mar 17 AM (10:30 - 12:10)
----------------------------------------

(38)/PRMU 10:30 - 10:45
Neural network generalization under optimally evolved training perturbations.
Subhajit Chaudhury, Toshihiko Yamasaki (UTokyo)

(39)/PRMU 10:45 - 11:00
Semi-Supervised Temporal Segmentation of Industrial Operation Video based on Deep Metric Learning
Daiki Kawamori, Kazuaki Nakamura, Naoko Nitta, Noboru Babaguchi (Osaka Univ.)

(40)/PRMU 11:00 - 11:15
Generating a 3D face with k-anonymity using GAN
Ryosuke Kobayashi, Yuta Nakashima, Noboru Babaguchi (Osaka Univ.)

(41)/PRMU 11:15 - 11:30
Method of Cloning Attack against Image Recognizer and Its Countermeasure
Shouta Kinbara, Kazuaki Nakamura, Naoko Nitta, Noboru Babaguchi (Osaka Univ.)

(42) 11:30 - 12:10


----------------------------------------
Tue, Mar 17 AM (10:30 - 12:10)
----------------------------------------

(43) 10:30 - 10:55


(44) 10:55 - 11:20


(45) 11:20 - 11:45


(46) 11:45 - 12:10


----- Break -----

----------------------------------------
Tue, Mar 17 PM (13:30 - 15:00)
----------------------------------------

(47) 13:30 - 14:15


(48) 14:15 - 15:00


----- Break -----

----------------------------------------
Tue, Mar 17 PM (15:15 - 16:40)
----------------------------------------

(49)/PRMU 15:15 - 15:30
Applicability of Television Archives to the Support for Memory Loss Aiming at Risk and Disaster Prevention
Norio Katayama, Hiroshi Mo, Shin'ichi Satoh (NII)

(50)/PRMU 15:30 - 15:45
Pedestrian Detection using Wide and Narrow Area Networks
Misaki Kodaira (Nagoya Univ.), Yu Wang, Jien Kato (Ritsumeikan Univ.)

(51)/PRMU 15:45 - 16:00
Ego-centric Activity Recognition of Rescue Dogs by Integrating visual, audio and sensor information
Yuta Ide, Tsuyohito Araki (UEC), Ryunosuke Hamada, Kazunori Ohno (Tohoku Univ.), Keiji Yanai (UEC)

(52)/PRMU 16:00 - 16:15
Acceleration of Deep Learning Inference by Model Cascading
Shohei Enomoto, Takeharu Eda (NTT)

(53) 16:15 - 16:40


----------------------------------------
Tue, Mar 17 PM (15:15 - 16:30)
----------------------------------------

(54) 15:15 - 15:40


(55) 15:40 - 16:05


(56) 16:05 - 16:30


----- Break -----

----------------------------------------
Tue, Mar 17 PM (16:50 - 17:35)
----------------------------------------

(57) 16:50 - 17:35


----------------------------------------
Tue, Mar 17 PM (16:50 - 18:00)
----------------------------------------

(58)/PRMU 16:50 - 17:05
Experimental Evaluation for Bayes Error Estimation Capability of Large Geometric Margin Minimum Classification Error Training
Ikuhiro Nishiyama (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.)

(59)/PRMU 17:05 - 17:20
Experimental Evaluation on Bayes Error Estimation Capability of Kernel Minimum Classification Error Training
Koji Yamada (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.)

(60)/PRMU 17:20 - 17:35
Study on Maximum Bayes Boundary-ness Training for Pattern Classification
Masahiro Senda, David Ha (Doshisha Univ.), Hideyuki Watanabe (ATR), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.)

(61) 17:35 - 18:00


# Information for speakers
General Talk will have 20 minutes for presentation and 5 minutes for discussion.

- This workshop has been cancelled. However, the technical report will be issued.


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

Thu, May 14, 2020 - Fri, May 15, 2020: online [Fri, Mar 6], Topics: Business based on computer vision and pattern recognition

# SECRETARY:
Contact address: prmu-organizer@mail.ieice.org

=== Special Interest Group on Computer Vision and Image Media (IPSJ-CVIM) ===
# FUTURE SCHEDULE:

Thu, May 14, 2020 - Fri, May 15, 2020: online [Fri, Mar 6], Topics: Business based on computer vision and pattern recognition


Last modified: 2020-02-26 23:22:16


Notification: Mail addresses are partially hidden against SPAM.

[Download Paper's Information (in Japanese)] <-- Press download button after click here.
 

[On-Site Price List of Paper Version of Proceedings (Technical Report)] (in Japanese)
 
[Presentation and Participation FAQ] (in Japanese)
 
[Cover and Index of IEICE Technical Report by Issue]
 

[Return to PRMU Schedule Page]   /   [Return to IPSJ-CVIM Schedule Page]   /  
 
 Go Top  Go Back   / [HTML] / [HTML(simple)] / [TEXT]  [Japanese] / [English] 


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan