Ryosuke Furuta

Research Interests

Optimization for Computer Vision and Image Processing.

Work Experience

Assistant Professor (Apr. 2019 - Sep. 2020)

Taniguchi Laboratory
Department of Information and Computer Technology, Tokyo University of Science, Japan

Visiting Researcher (May 2019 - Sep. 2020)

Yamasaki Laboratory
Department of Information and Communication Engineering, The University of Tokyo, Japan

Education

Ph.D., (Apr. 2016 - Mar. 2019)

Department of Information and Communication Engineering,
Graduate School of Information Science and Technology,
The University of Tokyo.
Advisor: Prof. Toshihiko Yamasaki

M.S., (Apr. 2014 - Mar. 2016)

Department of Information and Communication Engineering,
Graduate School of Information Science and Technology,
The University of Tokyo.
Advisor: Prof. Toshihiko Yamasaki

B.E., (Apr. 2010 - Mar. 2014)

Department of Information and Communication Engineering,
The University of Tokyo.
Advisor: Prof. Kiyoharu Aizawa and Prof. Toshihiko Yamasaki

Publications

Journals

• Ryosuke Furuta, Naoto Inoue, and Toshihiko Yamasaki
  PixelRL: Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
  IEEE TMM, 2020. (IEEE SPS Japan Young Author Best Paper Award) [arXiv] [IEEE Xplore] [project page] [code]

• Ryosuke Furuta, Naoto Inoue, and Toshihiko Yamasaki
  Efficient and Interactive Spatial-Semantic Image Retrieval
  MTAP, 2019. [pdf (open access)]

• Ryosuke Furuta, Satoshi Ikehata, Toshihiko Yamasaki, and Kiyoharu Aizawa
  Efficiency-Enhanced Cost-Volume Filtering featuring Coarse-to-Fine Strategy
  MTAP, 2018. [pdf (open access)] [code]

• Ryosuke Furuta, Ikuko Tsubaki, and Toshihiko Yamasaki
  Fast Volume Seam Carving with Multi-pass Dynamic Programming
  IEEE TCSVT, 2018. (Telecom System Technology Award 2018) [pdf (open access)] [video] [supplementary]

International conferences

• Delong Ouyang, Ryosuke Furuta, Yugo Shimizu, Yukinobu Taniguchi, Ryota Hinami, and Shonosuke Ishiwatari
  Interactive Manga Colorization with Fast Flat Coloring
  SIGGRAPH ASIA Posters, 2021.

• Xinyun Li, Ryosuke Furuta, Go Irie, and Yukinobu Taniguchi
  Accurate Indoor Localization using Multi-view Image Distance
  IEVC, 2021. (Best Student Paper Award)

• Risako Ii, Ryosuke Furuta, and Yukinobu Taniguchi
  Distortion Correction and Stitching of Overlapping Cattle Barn Images
  IEVC, 2021.

• Yugo Shimizu, Ryosuke Furuta, Delong Ouyang, Yukinobu Taniguchi, Ryota Hinami, and Shonosuke Ishiwatari
  Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks
  IEEE ICIP, 2021. [arXiv]

• Shunta Komatsu, Ryosuke Furuta, and Yukinobu Taniguchi
  Passenger Flow Estimation with Bipartite Matching on Bus Surveillance Cameras
  IEEE MIPR, 2021.

• Masaki Sugimoto, Ryosuke Furuta, and Yukinobu Taniguchi
  Weakly-Supervised Human-Object Interaction Detection
  VISAPP, 2021.

• Ryosuke Furuta, Naoaki Noguchi, Xueting Wang, and Toshihiko Yamasaki
  Feature Point Matching in Cross-Spectral Images with Cycle Consistency Learning
  ICPR, 2020.

• Ryosuke Furuta, Naoto Inoue, and Toshihiko Yamasaki
  Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
  AAAI, 2019. (acceptance rate 16.2%) [arXiv] [proceedings] [project page] [code]

• Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, and Kiyoharu Aizawa
  Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
  IEEE CVPR, 2018. (acceptance rate 29.1%) [pdf] [project page] [code]

• Ryosuke Furuta, Naoto Inoue, and Toshihiko Yamasaki
  Efficient and Interactive Spatial-Semantic Image Retrieval
  MMM, 2018. [pdf]

• Sijie Shen, Ryosuke Furuta, Toshihiko Yamasaki and Kiyoharu Aizawa
  Fooling Neural Networks in Face Attractiveness Evaluation: Adversarial Examples with High Attractiveness Score but Low Subjective Score
  IEEE BigMM (short paper), 2017.

• Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki and Kiyoharu Aizawa
  Object Detection Refinement Using Markov Random Field Based Pruning and Learning Based Rescoring
  IEEE ICASSP, 2017. [pdf]

• Ryosuke Furuta, Ikuko Tsubaki, and Toshihiko Yamasaki
  Fast Volume Seam Carving with Multi-pass Dynamic Programming
  IEEE ICIP, 2016. [pdf] [video]

• Ryosuke Furuta, Yusuke Fukushima, Toshihiko Yamasaki, and Kiyoharu Aizawa
  Multi-Label Classification using Class Relations Based on Higher-Order MRF Optimization
  IEEE CVPRW (BigVision), 2016. [pdf]

• Toshihiko Yamasaki, Yusuke Fukushima, Ryosuke Furuta, and Kiyoharu Aizawa
  Towards Online Prediction of Oral Presentation
  IEEE BigMM-ACM, 2016.

• Toshihiko Yamasaki, Yusuke Fukushima, Ryosuke Furuta, Litian Sun, Kiyoharu Aizawa, and Danushka Bollegala
  Prediction of User Ratings of Oral Presentations using Label Relations
  ACMMM-ASM, 2015.

• Ryosuke Furuta, Satoshi Ikehata, Toshihiko Yamasaki, and Kiyoharu Aizawa
  Coarse-to-Fine Strategy for Efficient Cost-Volume Filtering
  IEEE ICIP, 2014. (Top 10% Paper Award and IEEE SPS Japan Student Paper Award) [pdf]

Domestic conferences

• 68 papers

Awards

• Outstanding Presentation Award in Expressive Japan 2022. (three papers, co-author)
• Best Student Paper Award in IIEEJ International Conference on Image Electronics and Visual Computing (IEVC) 2021. (co-author)
• IIEEJ Research Encouragement Award, 2020. (co-author)
• IEEE Signal Processing Society (SPS) Japan Young Author Best Paper Award, 2020.
• IE Special Award, Technical Committee on Image Engineering, Institute of Electronics, Information and Communication Engineers, 2018.
• IE Award, Technical Committee on Image Engineering, Institute of Electronics, Information and Communication Engineers, 2018.
• Telecom System Technology Award, The Telecommunications Advancement Foundation, 2018.
• IE Award, Technical Committee on Image Engineering, Institute of Electronics, Information and Communication Engineers, 2015.
• IMPS Best and Frontier Paper Award, 2015. (co-author)
• IEEE Signal Processing Society (SPS) Japan Student Conference Paper Award, 2015.
• Harashima Hiroshi Science Award, Association for Promotion of Electrical, Electronic and Information Engineering, 2015.
• Top 10% Paper Award in IEEE International Conference on Image Processing (ICIP) 2014.
• ITE Outstanding Student Release Award, The Institute of Image Information and Television Engineers, 2013.
• ITE Suzuki Memorial Young Researcher's Award, The Institute of Image Information and Television Engineers, 2013.

Invited Talks

• Fast Image Processing with Multi-pass Dynamic Programming
  Image Processing Tokyo, Tokyo Institute of Technology, Jan. 2017.

Funding sources

• Grant-in-Aid for Early-Career Scientists, Japan Society for the Promotion of Science (JSPS). (FY2021 - FY2022)
• Grant-in-Aid for Research activity start-up, Japan Society for the Promotion of Science (JSPS). (FY2019 - FY2020)
• Research fellowship for young scientists (DC1), Japan Society for the Promotion of Science (JSPS). (FY2016 - FY2018)
• ITE Financial Support to International Conference Student Release, The Institute of Image Information and Television Engineers, 2014.

Links

Sato Laboratory/Sugano Laboratory

Institute of Industrial Science, The University of Tokyo

Taniguchi Laboratory

Tokyo University of Science

Yamasaki Laboratory

Graduate School of Information Science and Technology

The University of Tokyo

---