Mon, Feb 21 AM ME1 Chair: Takahiro Ogawa (Hokkaido Univ.) 10:30 - 11:45 |
(1) ME |
10:30-10:45 |
Automatic Feeding by Activity Determination Using Image Processing and Machine Learning for Fish Farming |
Yuto Takamatsu, Tokiya Seko, Satoshi Nakakoga, Nobuo Ezaki (NIT Toba), Tomohiko Kobayashi (Owase Lab) |
(2) ME |
10:45-11:00 |
Deer Detection and Feeding Pattern Derivation for Automatic Attraction in Vermin Cages |
Kota Himekomatsu, Riku Tsuji, Kazushige izue, Tsukasa kitahara, Satoshi Nakakoga, Nobuo Ezaki (NIT Toba), Osamu Takahashi (ISE), Naoto Yamabata (Hyogo Univ.) |
(3) ME |
11:00-11:15 |
RecipeLog: Input interface for multimedia recipes with structured instructions |
Akihisa Ishino, Yoko Yamakata (UTokyo), Hiroaki Karasawa (HSD), Sousuke Amano (foo.log), Kiyoharu Aizawa (UTokyo) |
(4) ME |
11:15-11:30 |
Datasets construction of first-person video capturing eating behavior toward automatic eat logging system |
Kenshiro Sato (UTokyo), Sosuke Amano (foo.log), Yoko Yamakata, Aizawa Kiyoharu (UTokyo) |
(5) ME |
11:30-11:45 |
A Study of Temporal Information Embedding in Group Activity Recognition Models |
Yuta Kumakura, Norio Tagawa (Tokyo Metropolitan Univ.), Shuhei Tarashima (NTT Communications Corp.) |
|
11:45-12:45 |
Lunch Break ( 60 min. ) |
Mon, Feb 21 PM ME2 Chair: Toshinori Hosoi (NEC) 12:45 - 13:45 |
(6) ME |
12:45-13:00 |
Quality Assessment for 3D CG Image Colorization Using Visible Digital Watermarking after Noise Removal Based on Sparse Dictionary Learning Coding |
Norifumi Kawabata (Hokkaido Univ.) |
(7) ME |
13:00-13:15 |
A note on multi-source model adaptation for semantic segmentation
-- Improving adaptation performance by learning model-invariant representation from multiple source models -- |
Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(8) ME |
13:15-13:30 |
A Note on Improvement of Accuracy in Classification of Distress Images for Efficient Inspection of Road Structures
-- Introduction of Ratio of Similar Cases Based on Text Data -- |
Taisei Hirakawa, Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(9) ME |
13:30-13:45 |
A Note on Automatic Diagnosis of Helicobacter Pylori Infection Based on Self-Supervised Learning and Self-Knowledge Distillation |
Guang Li, Ren Togo (Hokkaido Univ.), Katsuhiro Mabe (Junpukai Health Maintenance Center), Shunpei Nishida (Olympus), Yoshihiro Tomoda (Olympus Medical Systems), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
|
13:45-13:55 |
Break ( 10 min. ) |
Mon, Feb 21 PM MMS 13:55 - 14:55 |
(10) MMS |
13:55-14:10 |
Feasibility examination of detection of spatial quadrature amplitude modulated signal beam by single-shot transport of intensity equation method using polarization-dependent defocus control |
Kazuya Tashiro (Grad Sch of Fukuoka Univ.), Masatoshi Bunsen (Fukuoka Univ.) |
(11) MMS |
14:10-14:25 |
Experimental evaluation of parameter dependent performance of scattering imaging/scattering focusing using transmission matrix |
Tomoki Nakamura (Grad Sch of Fukuoka Univ.), Masatoshi Bunsen (Fukuoka Univ.) |
(12) MMS |
14:25-14:40 |
Improvement of learning process by transmission matrix in self-referential holographic neural network |
Rio Tomioka, Masanori Takabayashi (Kyushu Inst. of Tech) |
(13) MMS |
14:40-14:55 |
Effect of post-exposure time on diffraction efficiency of volume holograms during recording |
Yuya Kuroda, Atsushi Okamoto (Hokkaido Univ.), Satoshi Shinada, Yuta Goto (NICT), Akihisa Tomita (Hokkaido Univ.) |
|
14:55-15:05 |
Break ( 10 min. ) |
Mon, Feb 21 PM MMS, AIT 15:05 - 15:50 |
(14) MMS |
15:05-15:20 |
Mode diffusion technique for reduction of crosstalk in volume holographic mode demultiplexer |
Shuanglu Zhang, Atsushi Okamoto, Akihisa Tomita (Hokkaido Univ.) |
(15) MMS |
15:20-15:35 |
Resolution in 3D super-resolution projection using single-lens spatial cross modulation method |
Xinruinan Zhang, Atsushi Okamoto (Hokkaido Univ.), Hisatoshi Funakoshi (Gifu Univ.), Shuanglu Zhang, Akihisa Tomita (Hokkaido Univ.) |
(16) AIT |
15:35-15:50 |
Effects of foreground and unequal shielding on depth perception |
Nobutaka Natsui, Hisaki Nate, Kazuo Ishikawa (Tokyo Polytechnic Univ.) |
|
15:50-16:15 |
Break ( 25 min. ) |
Mon, Feb 21 PM ME5 Chair: Takahiro Mochizuki (NHK) 16:15 - 17:30 |
(17) ME |
16:15-16:30 |
A Note on Realizing Adversarial Defense Based on Regularization of Multi-stage Squeeze-and-Excitation Features |
Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(18) ME |
16:30-16:45 |
3D Light Source Direction Estimation Using Known Objects for Augmented Reality |
Yusuke Mukai, Hiroki Takahashi (UEC) |
(19) ME |
16:45-17:00 |
A Note on Disentanglement Using Deep Generative Model Based on Variational Autoencoder
-- Introduction of Regularization Losses Based on Metrics of Disentangled Representation -- |
Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(20) ME |
17:00-17:15 |
A Note on Interest level Estimation Using Users' Behavior Information
-- Validating the Effectiveness of Feature Integration with Multiple Users -- |
Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(21) ME |
17:15-17:30 |
A Note on User Preference-Aware Music Playlist Generation Based on Reinforcement Learning and Knowledge Graph |
Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Mon, Feb 21 AM IE1 10:45 - 11:45 |
(22) IEICE-IE |
10:45-11:00 |
User Satisfaction Prediction for Dialogue System in Mental Health Interventions |
Shengzhou Yi (UTokyo), Toshiaki Kikuchi (Keio), Toshihiko Yamasaki (UTokyo) |
(23) IEICE-IE |
11:00-11:15 |
Illustration author style translation using SailormoonRedraw data |
Keita Awane, Daichi Horita, Hikaru Ikuta, Yusuke Matsui (UTokyo), Naohiro Yanase (BOOK WALKER), Kiyoharu Aizawa (UTokyo) |
(24) IEICE-IE |
11:15-11:30 |
|
|
(25) IEICE-IE |
11:30-11:45 |
|
|
|
11:45-12:45 |
Lunch Break ( 60 min. ) |
Mon, Feb 21 PM IE2 12:45 - 13:45 |
(26) IEICE-IE |
12:45-13:00 |
Regularizing Generative Adversarial Networks with Internal Representation of Generators |
Yusuke Hara, Toshihiko Yamasaki (UTokyo) |
(27) IEICE-IE |
13:00-13:15 |
Domain Incremental Leaning with Adaptive Loss Functions |
Takumi Kawashima (UTokyo), Go Irie, Daiki Ikami (NTT), Kiyoharu Aizawa (UTokyo) |
(28) IEICE-IE |
13:15-13:30 |
Towards Universal Deep Image Compression |
Koki Tsubota (UTokyo), Hiroaki Akutsu (Hitachi), Kiyoharu Aizawa (UTokyo) |
(29) IEICE-IE |
13:30-13:45 |
Prediction of Seismic Intensity Distribution Using Neural Networks |
Haruki Mitarai, Koyu Mizutani, Kakeru Miyazaki, Ryugo Shimamura, Soichiro Kumano, Toshihiko Yamasaki (UTokyo) |
|
13:45-13:55 |
Break ( 10 min. ) |
Mon, Feb 21 PM ME3 Chair: Ayako Yamano (KONICA MINOLTA) 13:55 - 14:55 |
(30) ME |
13:55-14:10 |
A Note on Multi-label Image Recognition in Anime Illustration Based on Graph Convolutional Networks Using Captioning Features |
Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(31) ME |
14:10-14:25 |
A Note on Transformer-based Scene Recognition in Soccer Videos Using Different Lengths of Clips |
Yaozong Gan, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(32) ME |
14:25-14:40 |
A Note on Visual Sentiment Prediction Based on Few-shot Learning using Knowledge Distillation |
Yingrui Ye, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(33) ME |
14:40-14:55 |
A Note on Inspection Action Classification Using First and Third Person Video of Engineers Inspecting Bridges |
Tsuyoshi Masuda, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
|
14:55-15:05 |
Break ( 10 min. ) |
Mon, Feb 21 PM ME4, IE3 Chair: Toshihiko Yamasaki (Tokyo Univ.) 15:05 - 16:05 |
(34) ME |
15:05-15:20 |
A Note on Personalized Saliency Prediction Based on User Similarity Considering Object Information in Images |
Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(35) ME |
15:20-15:35 |
A Note on Electron Microscope Image Generation from Mix Proportion and Material Property via Generative Adversarial Network for Rubber Materials |
Rintaro Yanagi, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(36) IEICE-IE |
15:35-15:50 |
Liver Tumor Segmentation by Using a Massive-Training Artificial Neural Network (MTANN) and its Analysis in Liver CT. |
Yuqiao Yang, Muneyuki Sato, Ze Jin, Kenji Suzuki (Tokyo Tech) |
(37) IEICE-IE |
15:50-16:05 |
Statistical Analysis on Estimation of Laparoscopic Image Region of Interest Including Contrast Enhancement Based on Saliency Map |
Norifumi Kawabata (Hokkaido Univ.), Toshiya Nakaguchi (Chiba Univ.) |
|
16:05-16:15 |
Break ( 10 min. ) |
Mon, Feb 21 PM ITS1 16:15 - 17:30 |
(38) IEICE-ITS |
16:15-16:30 |
Adaptive Communication System Selection Method for V2X Using Wireless Environment Database |
Ayumu Ueda, Takeo Fujii, Atsuki Mukoda (UEC) |
(39) IEICE-ITS |
16:30-16:45 |
Constructing Packet Delivery Rate-Based Map for V2X Using Confidence Interval |
Atsuki Mukoda, Ayumu Ueda, Keita Katagiri, Takeo Fujii (UEC) |
(40) IEICE-ITS |
16:45-17:00 |
About the first floor of the Mode-separated-multi-layered type roundabout
-- Shared space for bicycles and pedestrians -- |
Zhao Kangbo, Hasegawa Takaaki (Saitama Univ.) |
(41) IEICE-ITS |
17:00-17:15 |
On the Safety and Efficiency on the Advanced Demand Signals Ⅱ scheme hyper
-- Can safety and efficiency be simultaneously achieved? -- |
Yuga Hirayama, Takaaki Hasegawa (Saitama Univ.) |
(42) IEICE-ITS |
17:15-17:30 |
A simulation-based study of traffic flow and crash related phenomena under the COVID-19 pandemic
-- Existence of the important peak -- |
Akira Kasahara, Takaaki Hasegawa, Ikkei Hasebe (Saitama Univ.) |
Tue, Feb 22 AM ITS2 10:15 - 11:00 |
(43) IEICE-ITS |
10:15-10:30 |
Classification of User's Device Possession Position and Behavior by Using Deep Metric Learning |
Rui Kitahara, Lifeng Zhang (Kyutech) |
(44) IEICE-ITS |
10:30-10:45 |
Interpolation Method for Sparse Point Cloud at Long-range Using Virtual RGB-D with LiDAR and Camera |
Mai Saito, Shuncong Shen, Toshio Ito (SIT) |
(45) IEICE-ITS |
10:45-11:00 |
Adaptive route planning for an autonomous driving setbox by potential field |
Chotaro Yamamoto, Toshio Ito (SIT) |
|
11:00-12:45 |
Lunch Break ( 105 min. ) |
Tue, Feb 22 AM IE4 10:00 - 11:00 |
(46) IEICE-IE |
10:00-10:15 |
Pretext-Contrastive Learning for Self-Supervised Video Feature Learning |
Li Tao (UTokyo), Xueting Wang (CyberAgent, Inc.), Toshihiko Yamasaki (UTokyo) |
(47) IEICE-IE |
10:15-10:30 |
Contrastive Self-Supervised Learning Framework for Unsupervised Video Summarization |
Xianliang Zhang, Li Tao (UTokyo), Xueting Wang (CyberAgent AI Lab), Toshihiko Yamasaki (UTokyo) |
(48) IEICE-IE |
10:30-10:45 |
A Length Controllable Model for Stylized Image Captioning |
Chi Zhang, Li Tao, Yamasaki Toshihiko (UTokyo) |
(49) IEICE-IE |
10:45-11:00 |
|
|
|
11:00-11:10 |
Break ( 10 min. ) |
Tue, Feb 22 AM IE5 11:10 - 12:10 |
(50) IEICE-IE |
11:10-11:25 |
Enhancing Personalized Food Image Classifier by Visual Attention and Class-Dependent Weighting |
Seum Kim, Yoko Yamakata, Kiyoharu Aizawa (UTokyo) |
(51) IEICE-IE |
11:25-11:40 |
Vector Font Generation for CJK Characters with Transformer |
Haruka Aoki, Kiyoharu Aizawa (UTokyo) |
(52) IEICE-IE |
11:40-11:55 |
English Situation-dependent Sentiment Polarity Dictionary |
Toshiki Matsumura, Atsushi Takada (UTokyo), Yoshinobu Kano (Shizuoka Univ.), Toshihiko Yamasaki (UTokyo) |
(53) IEICE-IE |
11:55-12:10 |
Bit-plane oriented Detection method of Malicious Code Hidden in the Image |
Ryo Kumagai, Shu Takemoto, Yusuke Nozaki, Masaya Yoshikawa (Meijo Univ.) |
|
12:10-13:00 |
Lunch Break ( 50 min. ) |
Tue, Feb 22 PM IE6 13:00 - 14:15 |
(54) IEICE-IE |
13:00-13:15 |
|
|
(55) IEICE-IE |
13:15-13:30 |
Noise-Resistant Learning for Object Detection |
Jiafeng Mao, Qing Yu, Yoko Yamakata, Kiyoharu Aizawa (UTokyo) |
(56) IEICE-IE |
13:30-13:45 |
What Kind of Images to Post on Instagram? Image Recommendation for Marketing |
Yiwei Zhang, Toshihiko Yamasaki (UTokyo) |
(57) IEICE-IE |
13:45-14:00 |
DeepFake detection using video and audio |
Tetsuo Uchida (TUT), Syunji Yazaki (UEC), Ishihata Hiroaki (TUT) |
(58) IEICE-IE |
14:00-14:15 |
|
|
|
14:15-14:25 |
Break ( 10 min. ) |
Tue, Feb 22 PM ITS4 14:25 - 15:10 |
(59) IEICE-ITS |
14:25-14:40 |
XR autonomous mobility platform for sense of movement |
Taishi Sawabe, Masayuki Kanbara, Yuichiro Fujimoto, Hirokazu Kato (NAIST) |
(60) IEICE-ITS |
14:40-14:55 |
A Study on Object Detection in Omnidirectional Images Using Deep Learning |
Yasuyuki Ishida, Toshio Ito (SIT) |
(61) IEICE-ITS |
14:55-15:10 |
3D Depth Estimation Based on Omnidirectional Epipolar Geometry |
Yuki Sakamura, Hidehiko Shishido, Itaru Kitahara (Univ. of Tsukuba) |
|
15:10-15:20 |
Break ( 10 min. ) |
Tue, Feb 22 PM ME7 Chair: Takahiro Mochizuki (NHK) 15:20 - 16:20 |
(62) ME |
15:20-15:35 |
A Note on Perceived Visual Content Estimation Based on Compressed Reconstruction Network Using Brain Signals While Gazing on Images |
Takaaki Higashi, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido University) |
(63) ME |
15:35-15:50 |
(%%% This presentation was CANCELLED)
The Rationale for Stability-Constrained Design of Variable Recursive Filters |
Tian-Bo Deng (Toho Univ.) |
(64) ME |
15:50-16:05 |
A Study on Region Estimation by Terminal Devices for Superimposing via Augmented Reality in Road Space |
Takayuki Abe, ShoTakahashi, Toru Hagiwara (Hokkaido Univ.) |
(65) ME |
16:05-16:20 |
A note on improvement of distress classification using noise barrier images on highway via object detection method |
Yun Liang, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
|
16:20-16:30 |
Break ( 10 min. ) |
Tue, Feb 22 PM ME8 Chair: Atsushi Hori (Mitsubishi Electric) 16:30 - 17:30 |
(66) ME |
16:30-16:45 |
Relevance Analysis between Bio-signals of Engineers Inspecting Subway Tunnels and Their Inspection Behaviors |
Kaito Hirasawa, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(67) ME |
16:45-17:00 |
A Note on Accurate Distress Classification Using Deep Learning Considering Confidence in Attention map |
Naoki Ogawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(68) ME |
17:00-17:15 |
A Note on Distress Detection based on Deep Learning with Hierarchical Multi-Scale Attention Mechanism for Supporting Maintenance of Subway Tunnels |
Saya Takada, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(69) ME |
17:15-17:30 |
A Study on Tracklet Appearance Feature Extraction for Multi-Target Multi-Camera Tracking |
Tomohiro Saito (Tokyo Metropolitan Univ.), Shuhei Trachima (NTT communications Corp.), Norio Tagawa (Tokyo Metropolitan Univ.) |
Tue, Feb 22 PM ME6, ITS3 Chair: Naohisa Hashimoto (AIST) 13:00 - 14:00 |
(70) ME |
13:00-13:15 |
Tracking System of Bowling Ball Based on Image Processing Using Multiple Cameras |
Khoo ShaoChuen, Ryosuke Sakai, Genki Suzuki, Hiroyuki Shioya (Muroran IT) |
(71) ME |
13:15-13:30 |
Compressive Sensing MR Reconstruction Using Generative Adversarial Network and Fresnel Transform of Images |
Shinya Abe, Kazuki Yamato, Satoshi Ito (Utsunomiya Univ.) |
(72) IEICE-ITS |
13:30-13:45 |
A Study on Performance Improvement of Target Positioning based on Multilateration |
Eichi Morita, Hiroyuki Hatano, Kosuke Sanada, Kazuo Mori (Mie Univ.), Asuka Tsujii, Takashi Kasashima (NGK SPARK PLUG), Takaya Yamazato (Nagoya Univ.) |
(73) IEICE-ITS |
13:45-14:00 |
Feasibility Study on Experimental Ridesharing System in Yurihonjo City, Akita |
Akari Suzuki, Kio Matsuda, Koichiro Hashiura, Yoshiyuki Kusakari, Ichiro Iida (Akita Prefectural Univ.), Yoshihiro Ito (Yurihonjo City) |
|
14:00-14:25 |
Break ( 25 min. ) |
Tue, Feb 22 PM IE7 14:25 - 14:55 |
(74) IEICE-IE |
14:25-14:40 |
Development of a Real Camera System with High-Level Synthesis Hardware of Median-Based Dynamic Background Subtraction |
Kohei Shinyamada, Akira Yamawaki (Kyutech) |
(75) IEICE-IE |
14:40-14:55 |
Detection of Physiological Disorders in European Pear Using HSV Color Features |
Noritaka Kubota, Tatsuya Yamazaki (Niigata Univ.) |