菅沼雅徳（Masanori Suganuma）

About me

Tohoku University, Assistant Professor

RIKEN AIP, Visiting Researcher

Mail: suganuma(at)vision.is.tohoku.ac.jp

March 2013
Division of Electrical and Computer Engineering, Faculty of Engineering, Yokohama National University (Grade-skipping). (B.E. in Engineering)
March 2015
Department of Information Media and Environment Sciences, Graduate School of Environment and Information Sciences, Yokohama National University. (M.E. in Engineering)
April 2015 - September 2017
Research Fellow (DC1) of the Japan Society for the Promotion of Science
September 2017
Department of Information Media and Environment Sciences, Graduate School of Environment and Information Sciences, Yokohama National University. (Ph.D. in Engineering)
October 2017 - September 2021
RIKEN AIP, Postdoctoral Fellow
November 2021 -
RIKEN AIP, visiting Researcher
October 2018 -
Tohoku University, Assistant Professor

Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features, European Conference on Computer Vision (ECCV), 2022 [PDF] [arXiv]

Wenzheng Song, Masanori Suganuma, Xing Liu, Noriyuki Shimobayashi, Daisuke Maruta, Takayuki Okatani: Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes, International Conference on Computer Vision (ICCV), 2021 [PDF] [arXiv]

Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks, International Joint Conference on Artificial Intelligence (IJCAI), 2021 [PDF] [arXiv]

Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani: Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs, European Conference on Computer Vision (ECCV), 2020 [PDF] [arXiv]

Masanori Suganuma, Xing Liu, Takayuki Okatani: Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [arXiv] [code] [poster]

Masanori Suganuma, Mete Ozay, Takayuki Okatani: Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search, The 35th International Conference on Machine Learning (ICML), 2018 [PDF] [arXiv] [code]

Masanori Suganuma, Shinichi Shirakawa, Tomoharu Nagao: A genetic programming approach to designing convolutional neural network architectures, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2017 (Best Paper Award) [PDF] [arXiv] [code(PyTorch)]

Outstanding Award, The institute of electrical engineers of Japan, September, 2018
Best Paper Award, GECCO 2017, July, 2017
Excellent Poster Award, STARC Forum 2015, November, 2015
Student Award, Yokohama National University (M.E.), March 2015
Student Award, The national convention of Information Processing Society of Japan, March 2013