English/Japanese

Yusuke Mukuta

Curriculum Vitae (in English, last update:10/27/2020)

News

07/23/2019
Our paper is accepted at ICCV.
06/06/2019
Our paper is accepted at MICCAI.
11/06/2018
Our paper is accepted at Astrophysical Journal. This is the product of the internship at National Astronomical Observatory of Japan.
11/01/2018
Our paper is accepted at AAAI.
10/16/2018
I work as a visiting researcher at RIKEN AIP.
04/01/2018
I work as an assistant professor at Machine Intelligence Lab. (The University of Tokyo)
11/08/2017
Two papers are accepted at AAAI. One paper is the product of the internship at NTT Communication Science Laboratories.
08/28/2017
Two papers are accepted at ICCV Workshops.
05/05/2016
Opened this page.

Affiliation

Machine Intelligence Lab
Dept. of Mechano-Informatics
Grad School of Information Science & Technology, The University of Tokyo (Japan)

Biography

October 2018 - Present
Visiting Researcher, RIKEN AIP
May 2018 - Present
Lecturer, Research Center for Advanced Science and Technology, the University of Tokyo
April 2018 - April 2020
Assistant Professor, Department of Mechano-Informatics, Graduate School of Information Science and Technology, the University of Tokyo
April 2017 - March 2018
JSPS Research Fellowship for Young Scientists (DC2)
August 2016
Internship at NTT Communication Science Laboratories
December 2013 - March 2014
Internship at National Astronomical Observatory of Japan
April 2015 - March 2018
PH. D of Information Science and Technology (The University of Tokyo)
April 2013 - March 2015
MA of Information Science and Technology (The Univeresity of Tokyo)
April 2009 - March 2013
BS of Engineering (The Univeresity of Tokyo)

Contact

e-mail: mukuta[at]mi.t.u-tokyo.ac.jp

Research Interest

Computer Vision, Machine Learning
Theory and Algorithm for Feature Extraction

Lecture

機械数学演習(2018年度A1A2)
リアルワールド認識(2019年度A1A2)

Publications

Preprint

  1. Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada. Hyperbolic Neural Networks++. arXiv:2006.08210, 2020.[arXiv]
  2. Wataru Kawai, Yusuke Mukuta, Tatsuya Harada. GRAM: Scalable Generative Models for Graphs with Graph Attention Mechanism. arXiv:1906.01861, 2019.[arXiv]
  3. Yusuke Mukuta, Tatsuya Harada. Invariant Tensor Feature Coding. arXiv:1906.01857, 2019.[arXiv]
  4. Yusuke Mukuta, Tatsuaki Machida, Tatsuya Harada. Compact Approximation for Polynomial of Covariance Feature. arXiv:1906.01851, 2019.[arXiv]
  5. Keisuke Hagiwara, Yusuke Mukuta, Tatsuya Harada. End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations. arXiv:1903.10118, 2019.[arXiv]

Journal

  1. Tadafumi Takata, Yusuke Mukuta, Yoshihiko Mizumoto. Modeling the Variability of Active Galactic Nuclei by Infinite Mixture of Ornstein-Uhlenbeck(OU) Processes. Astrophysical Journal, Volume 869, Number 2, pp.178-196 2018.[pdf][arXiv]

International Conference

  1. Yusuke Mori, Hiroaki Yamane, Yusuke Mukuta, Tatsuya Harada. Finding and Generating a Missing Part for Story Completion. In the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL) (COLING 2020, Workshop), accepted, 2020.
  2. Yuki Kawana, Yusuke Mukuta, Tatsuya Harada. Neural Star Domain as Primitive Representation. In the 34th Conference on Neural Information Processing Systems (Neurips 2020), accepted, 2020.
  3. Naoya Fushishita, Antonio Tejero-de-Pablos, Yusuke Mukuta, Tatsuya Harada. Long-Term Video Generation of Multiple Futures Using Human Poses. In the Advances in Image Manipulation Workshop and Challenges (ECCV 2020, Workshop), accepted, 2020.
  4. Yusuke Mori, Hiroaki Yamane, Yusuke Mukuta, Tatsuya Harada. Toward a Better Story End: Collecting Human Evaluation with Reasons. In the 12th International Conference on Natural Language Generation (INLG 2019), accepted, 2019.
  5. Kosuke Arase, Yusuke Mukuta, Tatsuya Harada. Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds. In the 4th Geometry Meets Deep Learning Workshop (ICCV 2019, Workshop), accepted, 2019.
  6. Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta, Hiroyuki Abe, Masashi Fukayama, Akihiko Yoshizawa, Masanobu Kitagawa, Tatsuya Harada. Multi-Stage Pathological Image Classification Using Semantic Segmentation. In the 17th International Conference on Computer Vision (ICCV 2019), accepted, 2019.
  7. Antonio Tejero-de-Pablos, Kaikai Huang, Hiroaki Yamane, Yusuke Kurose, Yusuke Mukuta, Yasushi Koyama, Junichi Iho, Youji Tokunaga, Makoto Horie, Keisuke Nishizawa, Yusaku Hayashi, Tatsuya Harada. Texture-based classification of significant stenosis in CCTA multi-view images of coronary arteries. In the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2019), accepted, 2019.
  8. Akane Iseki, Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Estimating the Causal Effect from Partially Observed Time Series. In the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), pp.3919-3926, 2019.[pdf]
  9. Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Alternating Circulant Random Features for Semigroup Kernels. In the 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), pp.3836-3843, 2018.[pdf]
  10. Yusuke Mukuta, Akisato Kimura, David Adrian, Zoubin Gharamani. Weakly Supervised Collective Feature Learning from Curated Media. In the 32nd AAAI Conference on Artificial Intelligence (AAAI 2018), pp.7260-7267, 2018.[pdf]
  11. Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Spatial-Temporal Weighted Pyramid using Spatial Orthogonal Pooling. In the 16th International Conference on Computer Vision Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision, pp.1041-1049, 2017.[pdf]
  12. Kuniaki Saito, Yusuke Mukuta, Yoshitaka Ushiku and Tatsuya Harada. Deep Modality Invariant Adversarial Network for Shared Representation Learning. In the 16th International Conference on Computer Vision Workshop on Transferring and Adapting Source Knowledge in Computer Vision, pp.2623-2629, 2017.[pdf]
  13. Yusuke Mukuta and Tatsuya Harada. Kernel Approximation via Empirical Orthogonal Decomposition for Unsupervised Feature Learning. the 29th IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2016), pp.5222-5230, 2016.[pdf][supplemental pdf]
  14. Yoshitaka Ushiku, Masataka Yamaguchi, Yusuke Mukuta, and Tatsuya Harada. Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images. the 14th International Conference on Computer Vision (ICCV 2015), pp.2668-2676, 2015.[pdf]
  15. Asako Kanezaki, Yusuke Mukuta, and Tatsuya Harada. Mirror Reflection Invariant HOG descriptors for Object Detection. the 21st IEEE International Conference on Image Processing (ICIP 2014), pp.1594-1598, 2014.[pdf]
  16. Yusuke Mukuta and Tatsuya Harada. Probabilistic Partial Canonical Correlation Analysis. the 31st International Conference on Machine Learning (ICML 2014), pp.1449-1457, 2014.[pdf][supplemental pdf][code]

Domestic Conference (In Japanese)

  1. 椋田悠介, 原田達也. 確率的偏正準相関分析. 信学技報, vol. 113, no. 286, IBISML2013-58, pp.169-176, 2013年11月.

Invited Talks

  1. Yusuke Mukuta and Tatsuya Harada. Probabilistic Partial Canonical Correlation Analysis. the 18th Meeting on Image Recognition and Understanding (MIRU 2015), 2015.
  2. Yusuke Mukuta, Yoshitaka Ushiku, Tatsuya Harada. Alternating Circulant Random Features for Semigroup Kernels. the 17th Forum on information Technology (FIT 2018), 2018.
  3. 椋田悠介. 幾何学的制約に基づくコンパクトな画像特徴量コーディング, PRMU, 2018年10月

Awards

  1. 2015 3rd place in the object detection task with external data. Large Scale Visual Recognition Challenge 2015 (ILSVRC2015).