Profile
Bio.
Hirokatsu Kataoka received his Ph.D. in engineering from Keio University in 2014. His research experience includes visiting scientist at Technical University of Munich (TUM) and JSPS Fellow (PD) at the University of Tokyo. Currently, he is a Senior Researcher at National Institute of Advanced Industrial Science and Technology (AIST). He also leads the cvpaper.challenge which conducts comprehensive survey and collaborative research in the field of computer vision and related academic fields. His research interest includes computer vision and pattern recognition, especially in large-scale dataset for image and video recognition. He has received ACCV 2020 Best Paper Honorable Mention Award, AIST 2019 Best Paper Award, and ECCV 2016 Workshop Brave New Idea.
-
Latest Professional Experience
Researcher, National Institute of Advanced Industrial Science and Technology (AIST)
(April 2016 - Present) -
Latest Education
Ph.D. in Engineering, Keio University
(April 2011 - March 2014)
What’s new?
-
Feb 05, 2021
Our research “Pre-training without Natural Images” was published in MIT Technology Review.
-
Nov 30, 2020
We won ACCV 2020 Best Paper Honorable Mention Award!
-
Nov 02, 2020
Our paper (novel-view image systhesis) was accepted to WACV 2021.
-
Oct 11, 2020
Two paper (Cycle Consistency, Generator Compression) were accepted to ICPR 2020.
-
Oct 02, 2020
Our paper (Virtual Try-on) was accepted to Sensors Journal (IF: 3.27).
Projects
-
cvpaper.challenge
We are finding a collaborator to read/write a sophisticated paper!
-
Pre-training without Natural Images
We would like to replace Supervised/Self-supervised Learning!
-
Alleviating Over-segmentation Errors by Detecting Action Boundaries
Detecting action boundary significantly improves segmentation performance.
-
View-agnostic Image Rendering
We generate novel-view images.
-
Scene Change Captioning
We can describe a change area in a real environment.
-
Weakly Supervised Person Dataset (WSPD)
Our weak-supervision surpassed a supervised pre-training.
-
Neural Joking Machine: Humorous image captioning
Now we are joking!
-
Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
We have collected large-scale traffic near-miss incident database!
-
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
3D Conv is ready to be used various video applications!
-
Dynamic Fashion Cultures
Now we can start a world-wide fashion analysis!
Selected Papers
-
Selected Papers Top-Rank
Hirokatsu Kataoka, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Yutaka Satoh, “Formula-driven Supervised Learning with Recursive Tiling Patterns,” ICCV 2021 Workshop on Human-centric Trustworthy Computer Vision: From Research to Applications, 2021.
-
Selected Papers Top-Rank
Ryosuke Yamada, Ryo Takahashi, Ryota Suzuki, Akio NAKAMURA, Yusuke Yoshiyasu, Ryusuke Sagawa, Hirokatsu Kataoka, “MV-FractalDB: Formula-driven Supervised Learning for Multi-view Image Recognition,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021. (Acceptance rate: 45.0%)
-
Selected Papers Top-Rank
Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka, “Alleviating Over-segmentation Errors by Detecting Action Boundaries,” Winter Conference on Applications of Computer Vision (WACV), 2021. (arXiv pre-print:2007.06866)
-
Selected Papers Top-Rank
Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh, “Pre-training without Natural Images”, Asian Conference on Computer Vision (ACCV), 2020. (Best Paper Honorable Mention Award; Oral Presentation; 3 Strong Accepts)
-
Selected Papers Top-Rank
Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka, “Retrieving and Highlighting Action with Spatiotemporal Reference,” IEEE International Conference on Image Processing (ICIP), 2020.