Journals (English) | Tsubasa Hirakawa

2025

Dorsoventral comparison of intraspecific variation in the butterfly wing pattern using a convolutional neural network

Kai Amino, Tsubasa Hirakawa, Masaya Yago, and Takashi Matsuo

Biology Letters, 2025

Bib HTML

@article{amino2025,
  author = {Amino, Kai and Hirakawa, Tsubasa and Yago, Masaya and Matsuo, Takashi},
  journal = {Biology Letters},
  title = {Dorsoventral comparison of intraspecific variation in the butterfly wing pattern using a convolutional neural network},
  year = {2025},
  volume = {21},
  no = {1},
  pages = {20240446}
}

2024

Adaptive Selection of Auxiliary Tasks Using Deep Reinforcement Learning for Video Game Strategy

Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi

IIEEJ Transaction on Image Electronics and Visual Computing (IEVC), 2024

Bib HTML

@article{itaya2024iieej,
  author = {Itaya, Hidenori and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {IIEEJ Transaction on Image Electronics and Visual Computing (IEVC)},
  title = {Adaptive Selection of Auxiliary Tasks Using Deep Reinforcement Learning for Video Game Strategy},
  year = {2024},
  volume = {12},
  no = {1},
  pages = {23--31}
}

Nearest neighbor future captioning: generating descriptions for possible collisions in object placement tasks

Takumi Komatsu, Motonari Kambara, Shumpei Hatanaka, Haruka Matsuo, and 4 more authors

Advanced Robotics, 2024

Bib HTML

@article{komatsu2024ar,
  author = {Komatsu, Takumi and Kambara, Motonari and Hatanaka, Shumpei and Matsuo, Haruka and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Sugiura, Komei},
  journal = {Advanced Robotics},
  number = {18},
  pages = {1265--1276},
  title = {Nearest neighbor future captioning: generating descriptions for possible collisions in object placement tasks},
  volume = {38},
  year = {2024}
}

Mask-Attention A3C: Visual Explanation of Action–State Value in Deep Reinforcement Learning

Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 1 more author

IEEE Access, 2024

Bib HTML

@article{itaya2024access,
  author = {Itaya, Hidenori and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Sugiura, Komei},
  journal = {IEEE Access},
  title = {Mask-Attention A3C: Visual Explanation of Action–State Value in Deep Reinforcement Learning},
  volume = {12},
  pages = {86553--86571},
  year = {2024}
}

Caption-Guided Interpretable Video Anomaly Detection Based on Memory Similarity

Yuzhi Shi, Takayoshi Yamashita, Tsubasa Hirakawa, Hironobu Fujiyoshi, and 3 more authors

IEEE Access, 2024

Bib HTML

@article{shi2024access,
  author = {Shi, Yuzhi and Yamashita, Takayoshi and Hirakawa, Tsubasa and Fujiyoshi, Hironobu and Nakazawa, Mitsuru and Chae, Yeongnam and Stenger, Björn},
  journal = {IEEE Access},
  title = {Caption-Guided Interpretable Video Anomaly Detection Based on Memory Similarity},
  volume = {12},
  pages = {63995--64005},
  year = {2024}
}

2023

Efficient Action Spotting Using Saliency Feature Weighting

Yuzhi Shi, Takayoshi Yamashita, Tsubasa Hirakawa, Hironobu Fujiyoshi, and 3 more authors

IEICE Transactions on Information and Systems, 2023

Bib HTML

@article{shi2023ieice,
  author = {Shi, Yuzhi and Yamashita, Takayoshi and Hirakawa, Tsubasa and Fujiyoshi, Hironobu and Kakazawa, Mitsuru and Chae, Yeongnam and Stenger, Björn},
  journal = {IEICE Transactions on Information and Systems},
  number = {1},
  pages = {105--114},
  title = {Efficient Action Spotting Using Saliency Feature Weighting},
  volume = {E107.D},
  year = {2023}
}

Toward Prototypical Part Interpretable Similarity Learning With ProtoMetric

Yuki Ukai, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi

IEEE Access, 2023

Bib HTML

@article{ukai2023access,
  author = {Ukai, Yuki and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {IEEE Access},
  pages = {62986--62997},
  title = {Toward Prototypical Part Interpretable Similarity Learning With ProtoMetric},
  volume = {11},
  year = {2023}
}

Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query

Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 1 more author

arXiv preprint, 2023

arXiv Bib
author = {Itaya, Hidenori and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Sugiura, Komei}, journal = {arXiv preprint}, year = {2023} }

Challenges and implications of predicting the spatiotemporal distribution of dengue fever outbreak in Chinese Taiwan using remote sensing data and deep learning

Sumiko Anno, Tsubasa Hirakawa, Satoru Sugita, Shinya Yasumoto, and 3 more authors

Geo-spatial Information Science, 2023

Bib HTML

@article{anno2023,
  author = {Anno, Sumiko and Hirakawa, Tsubasa and Sugita, Satoru and Yasumoto, Shinya and Lee, Ming-An and Sasaki, Yoshinobu and Oyoshi, Kei},
  journal = {Geo-spatial Information Science},
  number = {0},
  pages = {1--7},
  publisher = {Taylor & Francis},
  title = {Challenges and implications of predicting the spatiotemporal distribution of dengue fever outbreak in Chinese Taiwan using remote sensing data and deep learning},
  volume = {0},
  year = {2023}
}

Utilizing Human Social Norms for Multimodal Trajectory Forecasting via Group-Based Forecasting Module

Hiroaki Minoura, Tsubasa Hirakawa, Yusuke Sugano, Takayoshi Yamashita, and 1 more author

IEEE Transactions on Intelligent Vehicles, 2023

Bib HTML

@article{minoura2023ieeeiv,
  author = {Minoura, Hiroaki and Hirakawa, Tsubasa and Sugano, Yusuke and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {IEEE Transactions on Intelligent Vehicles},
  number = {1},
  pages = {836-850},
  title = {Utilizing Human Social Norms for Multimodal Trajectory Forecasting via Group-Based Forecasting Module},
  volume = {8},
  year = {2023}
}

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

Tomoya Nitta, Tsubasa Hirakawa, Hironobu Fujiyoshi, and Toru Tamaki

IEICE Transactions on Information and Systems, 2023

Bib HTML

@article{nitta2023ieice,
  author = {Nitta, Tomoya and Hirakawa, Tsubasa and Fujiyoshi, Hironobu and Tamaki, Toru},
  journal = {IEICE Transactions on Information and Systems},
  number = {3},
  pages = {391--400},
  title = {Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition},
  volume = {E106.D},
  year = {2023}
}

Automatic data collection for object detection and grasp-position estimation with mobile robots and invisible markers

Suraj Prakash Pattar, Thomas Killus, Tsubasa Hirakawa, Takayoshi Yamashita, and 2 more authors

Advanced Robotics, 2023

Bib HTML

@article{suraj2023ar,
  author = {Pattar, Suraj Prakash and Killus, Thomas and Hirakawa, Tsubasa and Yamashita, Takayoshi and Sawanobori, Tetsuya and Fujiyoshi, Hironobu},
  title = {Automatic data collection for object detection and grasp-position estimation with mobile robots and invisible markers},
  journal = {Advanced Robotics},
  volume = {37},
  number = {4},
  pages = {241--256},
  year = {2023},
  publisher = {Taylor & Francis}
}

2022

Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch

Yuya Maruyama, Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, and 2 more authors

arXiv preprint, 2022

arXiv Bib

  author = {Maruyama, Yuya and Fukui, Hiroshi and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Sugiura, Komei},
  journal = {arXiv preprint},
  title = {Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch},
  year = {2022}
}

A graph convolutional network for predicting COVID-19 dynamics in 190 regions/countries

Sumiko Anno, Tsubasa Hirakawa, Satoru Sugita, and Shinya Yasumoto

Frontiers in Public Health, 2022

Bib HTML

@article{anno2022covid,
  author = {Anno, Sumiko and Hirakawa, Tsubasa and Sugita, Satoru and Yasumoto, Shinya},
  journal = {Frontiers in Public Health},
  title = {A graph convolutional network for predicting COVID-19 dynamics in 190 regions/countries},
  volume = {10},
  year = {2022}
}

Single Suction Grasp Detection for Symmetric Objects Using Shallow Networks Trained with Synthetic Data

Suraj Prakash Pattar, Tsubasa Hirakawa, Takayoshi Yamashita, Tetsuya Sawanobori, and 1 more author

IEICE Transactions on Information and Systems, 2022

Bib HTML

@article{suraj2022ieice,
  author = {Pattar, Suraj Prakash and Hirakawa, Tsubasa and Yamashita, Takayoshi and Sawanobori, Tetsuya and Fujiyoshi, Hironobu},
  journal = {IEICE Transactions on Information and Systems},
  number = {9},
  pages = {1600--1609},
  title = {Single Suction Grasp Detection for Symmetric Objects Using Shallow Networks Trained with Synthetic Data},
  volume = {E105.D},
  year = {2022}
}

MT-DSSD: multi-task deconvolutional single shot detector for object detection, segmentation, and grasping detection

Ryosuke Araki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi

Advanced Robotics, 2022

Bib HTML

@article{araki2022ar,
  author = {Araki, Ryosuke and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {Advanced Robotics},
  number = {8},
  pages = {373--387},
  publisher = {Taylor & Francis},
  title = {MT-DSSD: multi-task deconvolutional single shot detector for object detection, segmentation, and grasping detection},
  volume = {36},
  year = {2022}
}

2021

ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition

Masahiro Mitsuhara, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi

arXiv preprint, 2021

arXiv Bib

  author = {Mitsuhara, Masahiro and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {arXiv preprint},
  title = {{ST-ABN:} Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition},
  year = {2021}
}

Normalization of VIIRS DNB images for improved estimation of socioeconomic indicators

Duc Chuc Man, Tsubasa Hirakawa, and Hiromichi Fukui

International Journal of Digital Earth, 2021

Bib HTML

@article{chuc2021ijde,
  author = {Man, Duc Chuc and Hirakawa, Tsubasa and Fukui, Hiromichi},
  journal = {International Journal of Digital Earth},
  number = {5},
  pages = {540--554},
  publisher = {Taylor & Francis},
  title = {Normalization of VIIRS DNB images for improved estimation of socioeconomic indicators},
  volume = {14},
  year = {2021}
}

Distant Traffic Light Recognition Using Semantic Segmentation

Shota Masaki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi

Transportation Research Record, 2021

Bib HTML

@article{masaki2021,
  author = {Masaki, Shota and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu},
  journal = {Transportation Research Record},
  number = {11},
  pages = {97--103},
  title = {Distant Traffic Light Recognition Using Semantic Segmentation},
  volume = {2675},
  year = {2021}
}

Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations

Aly Magassouba, Komei Sugiura, Angelica Nakayama, Tsubasa Hirakawa, and 3 more authors

Advanced Robotics, 2021

arXiv Bib HTML

@article{magassouba2021ar,
  author = {Magassouba, Aly and Sugiura, Komei and Nakayama, Angelica and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Kawai, Hisashi},
  journal = {Advanced Robotics},
  number = {12},
  pages = {787--799},
  publisher = {Taylor & Francis},
  title = {Predicting and attending to damaging collisions for placing everyday objects in photo-realistic simulations},
  volume = {35},
  year = {2021}
}

2020

Alleviating the Burden of Labeling: Sentence Generation by Attention Branch Encoder–Decoder Network

Tadashi Ogura, Aly Magassouba, Komei Sugiura, Tsubasa Hirakawa, and 3 more authors

IEEE Robotics and Automation Letters, 2020

arXiv Bib HTML

@article{ogura2020ral,
  author = {Ogura, Tadashi and Magassouba, Aly and Sugiura, Komei and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu and Kawai, Hisashi},
  journal = {IEEE Robotics and Automation Letters},
  number = {4},
  pages = {5945--5952},
  volume = {5},
  year = {2020}
}

2019

Deep learning-based image recognition for autonomous driving

Hironobu Fujiyoshi, Tsubasa Hirakawa, and Takayoshi Yamashita

IATSS Research, 2019

Bib HTML

@article{fujiyoshi2019IATSS,
  author = {Fujiyoshi, Hironobu and Hirakawa, Tsubasa and Yamashita, Takayoshi},
  journal = {IATSS Research},
  number = {4},
  pages = {244--252},
  title = {{Deep learning-based image recognition for autonomous driving}},
  volume = {43},
  year = {2019}
}

2018

Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning

Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki, Hironobu Fujiyoshi, and 4 more authors

Ecosphere, 2018

Bib HTML

@article{hirakawa2018ecosphere,
  author = {Hirakawa, Tsubasa and Yamashita, Takayoshi and Tamaki, Toru and Fujiyoshi, Hironobu and Umezu, Yuta and Takeuchi, Ichiro and Matsumoto, Sakiko and Yoda, Ken},
  journal = {Ecosphere},
  number = {10},
  pages = {e02447},
  title = {Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning},
  volume = {9},
  year = {2018}
}

2017

Tree-Wise Discriminative Subtree Selection for Texture Image Labeling

Tsubasa Hirakawa, Toru Tamaki, Takio Kurita, Bisser Raytchev, and 3 more authors

IEEE Access, 2017

Bib HTML

@article{hirakawa2017access,
  author = {Hirakawa, Tsubasa and Tamaki, Toru and Kurita, Takio and Raytchev, Bisser and Kaneda, Kazufumi and Wang, Chaohui and Najman, Laurent},
  journal = {IEEE Access},
  pages = {13617--13634},
  title = {Tree-Wise Discriminative Subtree Selection for Texture Image Labeling},
  volume = {5},
  year = {2017}
}

2016

Development of a Real-time Colorectal Tumor Classification System for Narrow-band Imaging zoom-videoendoscopy

Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, and 4 more authors

arXiv preprint, 2016

arXiv Bib

  author = {Hirakawa, Tsubasa and Tamaki, Toru and Raytchev, Bisser and Kaneda, Kazufumi and Koide, Tetsushi and Yoshida, Shigeto and Mieno, Hiroshi and Tanaka, Shinji},
  journal = {arXiv preprint},
  title = {Development of a Real-time Colorectal Tumor Classification System for Narrow-band Imaging zoom-videoendoscopy},
  year = {2016}
}

Domain Adaptation with L2 constraints for classifying images from different endoscope systems

Toru Tamaki, Shoji Sonoyama, Takio Kurita, Tsubasa Hirakawa, and 7 more authors

arXiv preprint, 2016

arXiv Bib

  author = {Tamaki, Toru and Sonoyama, Shoji and Kurita, Takio and Hirakawa, Tsubasa and Raytchev, Bisser and Kaneda, Kazufumi and Koide, Tetsushi and Yoshida, Shigeto and Mieno, Hiroshi and Tanaka, Shinji and Chayama, Kazuaki},
  journal = {arXiv preprint},
  title = {Domain Adaptation with {L2} constraints for classifying images from different endoscope systems},
  year = {2016}
}

Defocus-aware Dirichlet particle filter for stable endoscopic video frame recognition

Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, and 4 more authors

Artificial Intelligence in Medicine, 2016

Bib HTML

@article{hirakawa2016ddpf,
  author = {Hirakawa, Tsubasa and Tamaki, Toru and Raytchev, Bisser and Kaneda, Kazufumi and Koide, Tetsushi and Yoshida, Shigeto and Kominami, Yoko and Tanaka, Shinji},
  journal = {Artificial Intelligence in Medicine},
  pages = {1--16},
  title = {Defocus-aware Dirichlet particle filter for stable endoscopic video frame recognition},
  volume = {68},
  year = {2016}
}

Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy

Yoko Kominami, Shigeto Yoshida, Shinji Tanaka, Yoji Sanomura, and 6 more authors

Gastrointestinal Endoscopy, 2016

Bib HTML

@article{kominami2016,
  author = {Kominami, Yoko and Yoshida, Shigeto and Tanaka, Shinji and Sanomura, Yoji and Hirakawa, Tsubasa and Raytchev, Bisser and Tamaki, Toru and Koide, Tetsusi and Kaneda, Kazufumi and Chayama, Kazuaki},
  journal = {Gastrointestinal Endoscopy},
  number = {3},
  pages = {643--649},
  title = {Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy},
  volume = {83},
  year = {2016}
}

2013

Sa1668 Usefulness of Magnifying Endoscopy With Blue LASER Imaging for Diagnosis of Early Gastric Cancer

Rie Miyaki, Shigeto Yoshida, Shinji Tanaka, Yoko Kominami, and 12 more authors

Gastrointestinal Endoscopy, 2013

DDW Abstract Issue 2013

Bib HTML

@article{miyaki2013,
  author = {Miyaki, Rie and Yoshida, Shigeto and Tanaka, Shinji and Kominami, Yoko and Sanomura, Yoji and Matsuo, Taiji and Oka, Shiro and Hirakawa, Tsubasa and Raytchev, Bisser and Tamaki, Toru and Mishima, Tsubasa and Shigemi, Satoshi and Koide, Tetsushi and Kaneda, Kazufumi and Yoshihara, Masaharu and Chayama, Kazuaki},
  journal = {Gastrointestinal Endoscopy},
  note = {DDW Abstract Issue 2013},
  number = {5, Supplement},
  pages = {AB285},
  title = {Sa1668 Usefulness of Magnifying Endoscopy With Blue LASER Imaging for Diagnosis of Early Gastric Cancer},
  volume = {77},
  year = {2013}
}

Mo1642 Quantitative Analysis of NBI Magnifying Colonoscopy Images Based on Bag-of-Features for Diagnosis of Colorectal Tumors

Yoko Kominami, Shigeto Yoshida, Shinji Tanaka, Rie Miyaki, and 12 more authors

Gastrointestinal Endoscopy, 2013

DDW Abstract Issue 2013

Bib HTML

@article{kominami2013,
  author = {Kominami, Yoko and Yoshida, Shigeto and Tanaka, Shinji and Miyaki, Rie and Sanomura, Yoji and Matsuo, Taiji and Kanao, Hiroyuki and Oka, Shiro and Hirakawa, Tsubasa and Mishima, Tsubasa and Shigemi, Satoshi and Raytchev, Bisser and Tamaki, Toru and Koide, Tetsushi and Kaneda, Kazufumi and Chayama, Kazuaki},
  journal = {Gastrointestinal Endoscopy},
  note = {DDW Abstract Issue 2013},
  number = {5, Supplement},
  pages = {AB455--AB456},
  title = {Mo1642 Quantitative Analysis of NBI Magnifying Colonoscopy Images Based on Bag-of-Features for Diagnosis of Colorectal Tumors},
  volume = {77},
  year = {2013}
}