Satoshi Tsutsui

I am Satoshi Tsutsui, a Ph.D. candidate at School of Informatics, Computing, and Engineering, Indiana University, USA. I have been a Ph.D. student from 2015 Fall. I am very fortunate to work with Prof. David Crandall (advisor; committee chair), Prof. Chen Yu, and Prof. Ying Ding.

• Here is my formal resume
• Google Scholar: https://scholar.google.com/citations?user=tiXMNRIAAAAJ&hl=en
• E-Mail:
• Github: https://github.com/apple2373
• Twitter: https://twitter.com/satoshi2373

I am broadly interested in computer vision. Can we teach computers how to see as we do? This is a very challenging area of research, but it is also a very fun topic to work on! I have some experiences in object recognition, object detection, semantic segmentation, image captioning, few-shot learning, and first person vision. Please check my papers for the details.

I am also interested in deep learning, as a powerful tool for computer vision.

In the past, I have worked on: literature mining on Alzheimer’s disease, graph/network mining, semantic web, and linked data. 

Peer-reviewed Publications

• Satoshi Tsutsui, Yanwei Fu, David Crandall. (December 2019). Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition. Conference on Neural Information Processing Systems (NeurIPS).
  PDF Project Page Code
• Satoshi Tsutsui, Dian Zhi, Md Alimoor Reza, David Crandall, Chen Yu. (June 2019). Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study. Workshop on Egocentric Perception, Interaction and Computing (EPIC) , In conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR).
  arXiv:1906.01415 PDF
• Zheng Gao, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner, Brian Foote, David Wild, Qi Yu, Ying Ding. (2019). edge2vec: Representation learning using edge semantics for biomedical knowledge discovery. BMC Bioinformatics. (Impact Factor = 3.114). (accepted; to appear).
  arXiv:1809.02269 PDF
• Liang Ting-Ting, Mengyan Sun, Liangcai Gao, Jing-Jing Lu, Satoshi Tsutsui. (November 2018). APNet: Semantic Segmentation for PelvicMR Images. Chinese Conference on Pattern Recognition and Computer Vision (PRCV).
  arXiv:1806.00264 (Note: Arxiv version is slightly different from the conference version)
• Satoshi Tsutsui, Sven Bambach, David Crandall, Chen Yu. (October 2018). Estimating Head Motion from Egocentric Vision. ACM International Conference on Multimodal Interaction (ICMI).
  PDF
• Satoshi Tsutsui*, Tommi Kerola*, Shunta Saito*, David Crandall. (June 2018). Minimizing Supervision for Free-space Segmentation. Workshop on Autonomous Driving, In conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR).
  * The first three authors have equal contribution.
  arXiv:1711.05998 PDF code
• Satoshi Tsutsui, David Crandall. (Nov 2017). A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks. (oral presentation). The IAPR International Conference on Document Analysis and Recognition (ICDAR).
  arXiv:1703.05105 PDF Project Page Code (Figure Separation Tool)
• Satoshi Tsutsui, Tommi Kerola, Shunta Saito. (Oct 2017). Distantly Supervised Road Segmentation. Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving, In conjunction with International Conference on Computer Vision (ICCV).
  arXiv:1708.06118 PDF
• Satoshi Tsutsui, David Crandall. (July 2017). Using Artificial Tokens to Control Languages for Multilingual Image Caption Generation. Language and Vision Workshop, In conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR).
  arXiv:1706.06275 PDF Project Page Code (CNN + RNN caption generation)
• Baitong Chen, Satoshi Tsutsui, Ying Ding, Feicheng Ma. (2017). Understanding the topic evolution in a scientific domain: An exploratory study for the field of information retrieval. Journal of Informetrics, 11(4), 1175-1189. (Impact Factor = 2.920).
  URL
• Satoshi Tsutsui, Guilin Meng, Xiaohui Yao, David Crandall, Ying Ding. (Mar 2017). Analyzing Figures of Brain Images from Alzheimer's Disease Papers (poster). iConference.
  PDF Data
• Satoshi Tsutsui, Ying Ding, Guilin Meng. (Mar 2017). Public Machine Reading System for Alzheimer’s Disease Literature (poster). iConference.
• Satoshi Tsutsui, Ying Ding, Guilin Meng. (2016). Machine Reading Approach to Understand Alzheimer's Disease Literature, ACM 10th International Workshop on Data and Text Mining in Biomedical Informatics (DTMBIO), In conjunction with the Conference on Information and Knowledge Management (CIKM).
  PDF Demo Data

Education

September 2015 - Indiana University, Bloomington, Indiana, USA

• Master of Science in Data Science, May 2017
• Phd Student at School of Informatics, Computing, and Engineering
• GPA: 3.96 / 4.0

April 2011 - March 2015 Keio University, Japan

• Bachelor of Engineering in Administration Engineering, March 2015
• Major: Computer Science
• Graduation with the highest honor
• Overall GPA: 3.96 / 4.0
• Subject GPA: 3.96 / 4.0
• Research Adviser: Professor Takahira Yamaguchi.