Program

Your timezone (detected): JST

Note that the dates shown in the timetable is in Japan Time zone (JST). In your time zone, it may be off by one day. (E.g., for PDT, Day 1 starts on 24th.)

Timetable

	Day 1 July 25th		Day 2 July 26th		Day 3 July 27th
08:45		08:45		08:45	Poster 3 (w/ Oral 2-1) / MIRU2021 young researcher event (in Japanese)
09:00		09:00	Invited Talk 2 Dr. Chieko Asakawa How Technology Can Help the Visually Impaired Navigate the World	09:00
09:15	Opening	09:15		09:15
09:30	Invited Talk 1 Prof. Alexei A. Efros Self-supervision for Learning from the Bottom Up	09:30		09:30
09:45		09:45		09:45
10:00		10:00		10:00
10:15		10:15	Oral 2-1 Attentive and Structural Prediction	10:15	Invited Talk 3 Prof. Ming-Hsuan Yang Leaning to Enhance Images
10:30		10:30		10:30
10:45	Oral 1-1 Detection and Segmentation	10:45		10:45
11:00		11:00		11:00
11:15		11:15		11:15	Closing
11:30		11:30		11:30	Memorial Ceremony for Prof. Sakauchi
11:45		11:45		11:45	Memorial Ceremony for Prof. Sakauchi
12:00		12:00		12:00
break
13:00		13:00		13:00
13:15		13:15		13:15	Tutorial 1 Dr. Kris M. Kitani / MIRU2021 Tutorial 1 (in Japanese)
13:30		13:30		13:30
13:45		13:45		13:45
14:00		14:00		14:00
14:15	Poster 1 (w/ Oral 1-1, 1-2)	14:15	Oral 2-2 Robust and Adaptive Learning	14:15
14:30		14:30		14:30
14:45		14:45		14:45
15:00		15:00		15:00	Tutorial 2 Dr. Jingjing Chen / MIRU2021 Tutorial 2 (in Japanese)
15:15		15:15		15:15
15:30		15:30	Oral 2-3 Physics and Geometry based Modeling	15:30
15:45		15:45		15:45
16:00	Oral 1-2 Relationship Modeling	16:00		16:00
16:15		16:15		16:15
16:30		16:30		16:30
16:45		16:45	Poster 2 (w/ Oral 1-3, 2-2, 2-3)	16:45	Tutorial 3 Dr. Björn Stenger / MIRU2021 Tutorial 3 (in Japanese)
17:00		17:00		17:00
17:15	Oral 1-3 Action and Event Localization	17:15		17:15
17:30		17:30		17:30
17:45		17:45		17:45
18:00		18:00		18:00
18:15		18:15		18:15

Sessions

Sunday, July 25

09:15–09:30

Opening

09:30–10:30

Invited Talk 1

Self-supervision for Learning from the Bottom Up

Prof. Alexei A. Efros (UC Berkeley)

10:45–11:45

Oral 1-1 Detection and Segmentation

O1-1-1	Boosting Semi-Supervised Anomaly Detection via Contrasting Synthetic Images	Sheng-Feng Yu (Macronix International Co., Ltd.)*; Wei-Chen Chiu (National Chiao Tung University)
O1-1-2	Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution	Yuki Kondo (TTI-J)*; Norimichi Ukita (TTI-J)
O1-1-3	Distant Bird Detection for Safe Drone Flight and Its Dataset	Sanae Fujii (Toyota Technological Institute); Kazutoshi Akita (TTI-J)*; Norimichi Ukita (TTI-J)
O1-1-4	Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU	Napat Wanchaitanawong (Tokyo Institute of Technology)*; Masayuki Tanaka (Tokyo Institute of Technology); Takashi Shibata (NTT Corporation); Masatoshi Okutomi (Tokyo Institute of Technology)

14:15–15:45

Poster 1

This session includes the posters of Oral 1-1, 1-2.

P1-1	Machine-learning-based Quality-level-estimation System for Inspecting Steel Microstructures	Hiromi Nishiura (Hitachi,Ltd.)*; Atsushi Miyamoto (Hitachi,Ltd); Akira Ito (Hitachi,Ltd.); Shogo Suzuki (Hitachi Metals,Ltd.); Kouhei Fujii (Hitachi Metals,Ltd.); Hiroshi Morifuji (Hitachi Metals,Ltd.); Hiroyuki Takatsuka (Hitachi Metals,Ltd.)
P1-2	Contextual Information based Network with High-Frequency Feature Fusion for High Frame Rate and Ultra-Low Delay Small-Scale Object Detection	Dongmei Huang (Waseda University)*; Jihan Zhang (Waseda University); Tingting Hu (Waseda University); Ryuji Fuchikami (Panasonic); Takeshi Ikenaga (Waseda University)
P1-3	Position Estimation of Pedestrians in Surveillance Video using Face Detection and Simple Camera Calibration	Toshio Sato (Waseda University)*; Xin Qi (Waseda University); keping yu (Waseda University); Zheng Wen (Waseda Universiy); Yutaka Katsuyama (Waseda University); Takuro Sato (waseda university)
P1-4	Facial landmark detection transfer learning for a specific user in driver status monitoring systems	Jaechul Kim (Kyocera Corporation)*; Kensuke Taguchi (Kyocera Corporation); Yusuke Hayashi (Kyocera Corporation); Jungo Miyazaki (Kyocera Corporation); Hironobu Fujiyoshi (Chubu University)
P1-5	FBNet: FeedBack-Recursive CNN for Saliency Detection	Guanqun Ding (University of Tsukuba)*; Nevrez Imamoglu (AIST); Ali Caglayan (National Institute of Advanced Industrial Science and Technologhy (AIST), Tokyo, Japan); Masahiro Murakawa (National Institute of Advanced Industrial Science and Technology (AIST)); Ryosuke Nakamura (National Institute of Advanced Industrial Science and Technology)
P1-6	Angular Margin Constrained Loss for Automatic Liver Fibrosis Staging	Katsuhiro Nakai (Yamaguchi University)*; Xu Qiao (Shandong University); Xian-Hua Han (Yamaguchi University)
P1-7	Attention Mining Branch for Optimizing Attention Map	Takaaki Iwayoshi (Chubu University)*; Masahiro Mitsuhara (Chubu University); Masayuki Takada (Chubu University); Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University)
P1-8	Critically Compressed Quantized Convolution Neural Network based High Frame Rate and Ultra-Low Delay Fruit External Defects Detection	Jihan Zhang (Waseda University)*; Dongmei Huang (Waseda University); Tingting Hu (Waseda University); Ryuji Fuchikami (Panasonic); Takeshi Ikenaga (Waseda University)
P1-9	Lossless AI: Toward Guaranteeing Consistency between Inferences Before and After Quantization via Knowledge Distillation	Tomoyuki Okuno (Panasonic)*; Yohei Nakata (Panasonic); Yasunori Ishii (Panasonic); Sotaro Tsukizawa (Panasonic)
P1-10	Joint Learning of Object Detection and Pose Estimation using Augmented Autoencoder	Ryota Hayashi (TTI-J); Asei Shimokura (TTI-J)*; Takuya Matsumoto (TTI-J); Norimichi Ukita (TTI-J)
P1-11	Relational Subgraph for Graph-based Path Prediction	masaki miyata (chubu university)*; Katsutoshi Shiraki (Chubu University); Hiroaki Minoura (Chubu University); Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University)
P1-12	Image Information Assistance Neural Network for VideoPose3D-based Monocular 3D Pose Estimation	Hao Wang (Waseda University)*; Dingli Luo (Waseda University); Takeshi Ikenaga (Waseda University)
P1-13	Video Summarization With Frame Index Vision Transformer	Tzu-Chun Hsu (National Chung Hsing University); Yi-Sheng Liao (National Chung Hsing University); Chun-Rong Huang (National Chung Hsing University)*
P1-14	Multi-physical and Temporal Feature Based Self-correcting Approxi-mation Model for Monocular 3D Volleyball Trajectory Analysis	Jiaxu Dong (Waseda University)*; Xina Cheng (Xidian University); Takeshi Ikenaga (Waseda University)
P1-15	Japanese Sentence Dataset for Lip-reading	Tatsuya Shirakata (Kyushu Institute of Technology); Takeshi Saitoh (Kyushu Institute of Technology)*

16:00–17:00

Oral 1-2 Relationship Modeling

O1-2-1	Human-Object Interaction Detection with Missing Objects	Kaen Kogashi (kyoto university)*; Yang Wu (Kyoto University); Shohei Nobuhara (Kyoto University); Ko Nishino (Kyoto University)
O1-2-2	Group Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping	Chihiro Nakatani (TTI-J)*; Kohei Sendo (TTI-J); Norimichi Ukita (TTI-J)
O1-2-3	Saliency based Subject Selection for Diverse Image Captioning	An Quoc Luong (The Graduate University for Advanced Studies, SOKENDAI)*; Minh-Duc Vo (The University of Tokyo); Akihiro Sugimoto (NII)
O1-2-4	Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval	Ming Zhang (City University of Hong Kong)*

17:15–18:15

Oral 1-3 Action and Event Localization

O1-3-1	Live Video Action Recognition from Unsupervised Action Proposals	Roberto Javier Lopez-Sastre (University of Alcala)*; Marcos Baptista-Rios (Gradiant); Francisco J. Acevedo-Rodríguez (University of Alcalá); Pilar Martín Martín (universidad de Alcalá); Saturnino Maldonado-Bascon (Universidad de Alcalá)
O1-3-2	Action Spotting and Temporal Attention Analysis of Events in Soccer Videos	Hiroaki Minoura (Chubu University)*; Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University); Mitsuru Nakazawa (Rakuten Institute of Technology, Rakuten Group, Inc.); Yeongnam Chae (Rakuten Institute of Technology); Bjorn Stenger (Rakuten Institute of Technology)
O1-3-3	Selecting an Iconic Pose From an Action Video	Geethu Jacob (Rakuten Institute of Technology); Bjorn Stenger (Rakuten Institute of Technology)*
O1-3-4	Leveraging Frequency Based Salient Spatial Sound Localization to Improve 360° Video Saliency Prediction	Mert Cokelek (Hacettepe University)*; Nevrez Imamoglu (AIST); Cagri Ozcinar (Samsung); Erkut Erdem (Hacettepe University); Aykut Erdem (Koc University)

Monday, July 26

09:00–10:00

Invited Talk 2

How Technology Can Help the Visually Impaired Navigate the World

Dr. Chieko Asakawa (IBM)

10:15–11:15

Oral 2-1 Attentive and Structural Prediction

O2-1-1	Augmenting Discriminative Correlation Filters with Stereo Blob Tracking for Long-Term Tracking of Underwater Animals	Miao Zhang (Stanford University)*; Stephen Rock (Stanford University)
O2-1-2	Predicting Next Local Appearance for Video Anomaly Detection	Pankaj PRR Roy (École Polytechnique de Montréal)*; Guillaume-Alexandre Bilodeau (Polytechnique Montréal); Lama Seoud (Polytechnique Montreal)
O2-1-3	HMA-Depth: A New Monocular Depth Estimation Model Using Hierarchical Multi-Scale Attention	Zhaofeng Niu (NAIST)*; Yuichiro Fujimoto (NAIST); Masayuki Kanbara (Nara Institute of Science and Technology); Hirokazu Kato (NAIST)
O2-1-4	Shape-Based Floor Plan Retrieval Using Parse Tree Matching	Philip Kenneth Lee (Stanford University); Bjorn Stenger (Rakuten Institute of Technology)*

14:15–15:15

Oral 2-2 Robust and Adaptive Learning

O2-2-1	Estimating Contribution of Training Datasets using Shapley Values in Data-scale for Visual Recognition	Takayuki Semitsu (Mitsubishi Electric Corporation)*; Mitsuki Nakamura (Mitsubishi Electric Corporation); Shotaro Ishigami (Mitsubishi Electric Corporation ); Teng-Yok Lee (Mitsubishi Electric); Toru Aoki (Mitsubishi Electric Corporation); Yoshimi Isu (Mitsubishi Electric Corporation)
O2-2-2	Data Augmentation for Human Motion Prediction	Takahiro Maeda (TTI-J)*; Norimichi Ukita (TTI-J)
O2-2-3	Content Filtering in Streaming Video Using Domain Adaptation	Utsav Shah (Rakuten Institute of Technology)*; Muhammad Rasyid Aqmar (Bukalapak); Mitsuru Nakazawa (Rakuten Institute of Technology, Rakuten Group, Inc.); Bjorn Stenger (Rakuten Institute of Technology)
O2-2-4	Occlusion-Robust 3D Hand Pose Estimation from a Single RGB Image	Asuka Ishii (NEC)*; Gaku Nakano (NEC Corporation); Tetsuo Inoshita (NEC)

15:30–16:30

Oral 2-3 Physics and Geomety based Modeling

O2-3-1	Information Hiding Using a Coded Aperture as a Key	Tomoki Minamata (Kagoshima University)*; Shoma Ishida (Kagoshima University); Shingo Takeshita (Kagoshima University); Hiroshi Kawasaki (Kyushu univ.); Hajime Nagahara (Osaka University); Satoshi Ono (Kagoshima University)
O2-3-2	An Optical Model for Show-through Cancellation in Ancient Document Imaging with Dark and Bright Mounts	Yuri Ueno (Nara Institute of Science and Technology)*; Kenichiro Tanaka (Ritsumeikan University); Takuya Funatomi (Nara Institute of Science and Technology); Yasuhiro Mukaigawa (NAIST)
O2-3-3	Self-Supervised Deep Fisheye Image Rectification Approach using Coordinate Relations	Masaki Hosono (Waseda University)*; Edgar Simo-Serra (Waseda University); Tomonari Sonoda (Utagoe Inc.)
O2-3-4	Expandable Spherical Projection and Feature Fusion Methods for Object Detection from Fisheye Images	Songeun Kim (Kyungpook National University); Soon Yong Park (Kyungpook National University)*

16:45–18:15

Poster 2

This session includes the posters of Oral 1-3, 2-2, 2-3.

P2-1	Temporal Extension for Encoder-Decoder-based Crowd Counting Approaches	Thomas Golda (Karlsruhe Institute of Technology)*; Florian Krüger (Fraunhofer Insitute for Optronics, System Technologies and Image Exploitation IOSB); Jürgen Beyerer (Fraunhofer IOSB)
P2-2	Model-based Crack Width Estimation using Rectangle Transform	Christian Benz (Bauhaus-Universität Weimar)*; Volker Rodehorst (Bauhaus-Universität Weimar)
P2-3	A baseline for semi-supervised learning of efficient semantic segmentation models	Ivan Grubišić (University of Zagreb, Faculty of Electrical Engineering and Computing)*; Marin Oršić (UNIZG-FER); Sinisa Segvic (UniZg-FER)
P2-4	Efficient transfer learning for multi-channel convolutional neural networks	Aloïs de La Comble (Rakuten)*; Ken Prepin (Rakuten)
P2-5	On the Influence of Viewpoint Change for Metric Learning	Marco Filax (Chair of Software Engineering, OvGU Magdeburg)*; Frank Ortmeier (Chair of Software Engineering, OvGU Magdeburg)
P2-6	Analysis of Evaluation Metrics with the Distance between Positive Pairs and Negative Pairs in Deep Metric Learning	Hajime Oi (The University of Tokyo)*; Rei Kawakami (Tokyo Institute of Technology); Takeshi Naemura (The University of Tokyo)
P2-7	Seeing Farther Than Supervision: Self-supervised Depth Completion in Challenging Environments	Seiya Ito (Aoyama Gakuin University)*; Naoshi Kaneko (Aoyama Gakuin University); Kazuhiko Sumi (Aoyama Gakuin University)
P2-8	Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport	Rémy Leroy (ONERA)*; Pauline Trouvé (ONERA); Frédéric Champagnat (ONERA); Bertrand Le Saux (ESA / Phi-lab); Marcela Carvalho (Upciti)
P2-9	Practical Descattering of Transmissive Inspection Using Slanted Linear Image Sensors	Takahiro Kushida (Nara Institute of Science and Technology)*; Kenichiro Tanaka (Ritsumeikan University); Takuya Funatomi (Nara Institute of Science and Technology); Komei Tahara (Vienex Corporation); Yukihiro Kagawa (Vienex Corporation); Yasuhiro Mukaigawa (NAIST)
P2-10	Recurrent RLCN-Guided Attention Network for Single Image Deraining	Yizhou Li (Tokyo Institute of Technology)*; Yusuke Monno (Tokyo Institute of Technology); Masatoshi Okutomi (Tokyo Institute of Technology)
P2-11	AVM Image Quality Enhancement by Synthetic Image Learning for Supervised Deblurring	Kazutoshi Akita (TTI-J)*; Masayoshi Hayama (TTI-J); Haruya Kyutoku (Toyota Technological Institute); Norimichi Ukita (TTI-J)
P2-12	Shape from shading and polarization constrained by approximate shape	Wataru Muraoroshi (Hiroshima City University); Daisuke Miyazaki (Hiroshima City University)*
P2-13	Illumination Planning for Measuring Per-Pixel Surface Roughness	Kota Arieda (Kyushu Institute of Technology); Takahiro Okabe (Kyushu Institute of Technology)*
P2-14	ROT-Harris: A Dynamic Approach to Asynchronous Interest Point Detection	Shane P Harrigan (Ulster University)*; Sonya Coleman (School of Computing and Intelligent Systems, University of Ulster); Dermot Kerr (Ulster University); Dr. Yogarajah Pratheepan (Ulster University, UK); Zheng Fang (Northeastern University); Chengdong Wu (Northeastern University)
P2-15	Encoding-free Incrementing Hough Transform for High Frame Rate and Ultra-low Delay Straight-line Detection	Ziwei Dong (Waseda University)*; Tingting Hu (Waseda University); Ryuji Fuchikami (Panasonic); Takeshi Ikenaga (Waseda University)

Tuesday, July 27

08:45–10:00

Poster 3

This session includes the posters of Oral 2-1.

P3-1	Open-set Recognition with Supervised Contrastive Learning	Yuto Kodama (The University of Tokyo); Yinan Wang (The University of Tokyo)*; Rei Kawakami (Tokyo Institute of Technology); Takeshi Naemura (The University of Tokyo)
P3-2	Learning VAE with Categorical Labels for Generating Conditional Handwritten Characters	Keita Goto (Tokyo Institute of Technology)*; Nakamasa Inoue (Tokyo Institute of Technology)
P3-3	Understanding the Reason for Misclassification by Generating Counterfactual Images	Muneaki Suzuki (Meijo University); Yoshitaka Kameya (Meijo University)*; Takuro Kutsuna (DENSO CORPORATION); Naoki Mitsumoto (DENSO CORPORATION)
P3-4	Adversarial Defense Through High Frequency Loss Variational Autoencoder Decoder and Bayesian Update With Collective Voting	Zhixun He (University of California, Merced)*; Mukesh Singhal (UC Merced)
P3-5	Weakly Supervised Domain Adaptation using Super-pixel labeling for Semantic Segmentation	Masaki Yamazaki (Honda)*; Xingchao Peng (Boston University); Kuniaki Saito (Boston University); Ping Hu (Boston University); Kate Saenko (Boston University); Yasuhiro Taniguchi (Honda)
P3-6	Output augmentation works well without any domain knowledge	Shu Eguchi (Fukuoka University)*; Ryo Nakamura (Fukuoka University); Masaru Tanaka (Fukuoka University)
P3-7	Cut and paste curriculum learning with hard negative mining for point-of-sale systems	Jaechul Kim (Kyocera Corporation)*; Xiaoyan Dai (Kyocera Coporation); Yisan Hsieh (Kyocera Coporation); Hiroki Tanimoto (Kyocera Coporation); Hironobu Fujiyoshi (Chubu University)
P3-8	Synthetically Generating Motion Blur in a Depth Map from Time-of-Flight Sensors	Bryan D Rodriguez (Southern Methodist University)*; Xinxiang Zhang (Southern Methodist University); Dinesh Rajan (Southern Methodist University)
P3-9	Bi-directional Recurrent MVSNet for High-resolution Multi-view Stereo	Taku Fujitomi (Aoyama Gakuin University)*; Seiya Ito (Aoyama Gakuin University); Naoshi Kaneko (Aoyama Gakuin University); Kazuhiko Sumi (Aoyama Gakuin University)
P3-10	Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction	Hajime Taira (Tokyo Institute of Technology)*; Koki Onbe (Tokyo Institute of Technology); Naoyuki Miyashita (Olympus R&D.); Masatoshi Okutomi (Tokyo Institute of Technology)
P3-11	Multiple Fisheye Camera Calibration and Stereo Measurement Methods for Uniform Distance Errors throughout Imaging Ranges	Nobuhiko Wakai (Panasonic Corporation)*; Takeo Azuma (OmniVision Technologies, Inc); Kunio Nobori (Panasonic Corporation)