I am Satoshi Tsutsui, a Ph.D. student at School of Informatics, Computing, and Engineering. I started my Ph.D. life at 2015 Fall. I am advised by Prof. David Crandall and Prof. Ying Ding.
I am intereted in the general area of computer vision; Can we teach computers how to see as we do? This is very challenging research area but also very fun domain to work on! I have some experiences in basic image understanding problems such as
and caption generation.
Please find my papers for the details.
I am also intereted in deep learning, as a powerful tool for computer vison. I have used chainer and tensorflow. You can find implementations in my github.
I am currently interested in applying computer vision for understanding scientific figures (e.g., diagrams appearing in CVPR papers ) and the relation between figures and the paper's scientific impact (i.e., citations). For example, can we extract the neural net architecture from the figures in CVPR? What kind of figures can maximize the citation if you include in your paper?
In the past, I have worked on: literature mining on Alzheimer’s disease, graph/network mining, semantic web, and linked data . I learned semantic web technologies in my undergraduate research program. I extended DBpedia using list structure in Wikipedia pages. If you are interested, please refer to this unpublished paper.
Tsutsui, S., Crandall, D. (Nov 2017) A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks. The IAPR International Conference on Document Analysis and Recognition (ICDAR).
Code (Figure Separation Tool)
Tsutsui, S., Kerola, T., Saito, S. (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).
Tsutsui, S., Crandall, D. (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).
Code (CNN + RNN caption generation)
Tsutsui, S., Meng, G., Yao, X., Crandall, D., Ding, Y. (Mar 2017) Analyzing Figures of Brain Images from Alzheimer's Disease Papers (poster). iConference.
- Tsutsui, S., Meng, G, Ding, Y. (Mar 2017). Public Machine Reading System for Alzheimer’s Disease Literature (poster). iConference.
- Tsutsui, S., Ding, Y, Meng, G, 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).
September 2015 - Indiana University, Bloomington, Indiana, USA
- Phd Student at School of Informatics, Computing, and Engineering
- GPA: 4.0
April 2011 - March 2015 Keio University, Japan
- Bachelor of Engineering in Administration Engineering, March 2015
- Major: Computer Science
- Gradutation with the highest honor
- Overall GPA: 3.96
- Subject GPA: 3.96
- Research Adviser: Professor Takahira Yamaguchi ,Ph.D.
- Thesis: "Extending DBpedia Property with List Structures in Wikipedia Articles