Publications

For an idea that does not first seem insane, there is no hope - Alboert Ainstain

Image

Spatiotemporal Initialization for 3D CNNs with Generated Motion Patterns

In Winter Conference on Applications of Computer Vision (WACV) 2022

Hirokatsu Kataoka, Eisuke Yamagata, Kensho Hara, Ryusuke Hayashi, Nakamasa Inoue
Project Page

Image

Formula-driven Supervised Learning with Recursive Tiling Patterns

In ICCV 2021 Workshop on Human-centric Trustworthy Computer Vision (HTCV) 2021

Hirokatsu Kataoka, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Yutaka Satoh
Project PagePDF

Image

Describing and Localizing Multiple Change with Transformers

In International Conference on Computer Vision (ICCV) 2021

Yue Qiu*, Shintaro Yamamoto*, Kodai Nakashima, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, Yutaka Satoh
Project PagePDF

Image

A Case Study on User Evaluation of Scientific Publication Summarization by Japanese Students

In Applied Sciences 2021, 11(14), 6287

Shintaro Yamamoto, Ryota Suzuki, Tsukasa Fukusato, Hirokatsu Kataoka, Shigeo Morishima
PDF

Image

MV-FractalDB: Formula-driven Supervised Learning for Multi-view Image Recognition

In International Conference on Intelligent Robots and Systems (IROS) 2021

Ryosuke Yamada, Ryo Takahashi, Ryota Suzuki, Akio Nakamura, Yusuke Yoshiyasu, Ryusuke Sagawa, Hirokatsu Kataoka
Project Page

Image

Robust Self-Trained Person Detection for Vulnerable Road Users

In CVPR 2021 Workshop on Beyond Fairness: Towards a Just, Equitable, and Accountable Computer Vision (BeyondFairCV) 2021

Shunsuke Kogure, Kai Watabe, Ryosuke Yamada, Yoshimitsu Aoki, Akio Nakamura, Hirokatsu Kataoka
Project PagePDF

Image

Rethinking Training Data for Mitigating Representation Biases in Action Recognition

In CVPR 2021 Workshop on Large Scale Holistic Video Understanding 2021

Kensho Hara, Yuchi Ishikawa, Hirokatsu Kataoka

Image

Alleviating Over-segmentation Errors by Detecting Action Boundaries

In Winter Conference on Applications of Computer Vision (WACV) 2021

Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka
Project PagePDFCode

Image

Viewpoint-agnostic Image Rendering

In Winter Conference on Applications of Computer Vision (WACV) 2021

Hiroaki Aizawa, Hirokatsu Kataoka, Yutaka Satoh, Kunihito Kato
Project PagePDF

Image

Pre-training without Natural Images

In Asian Conference on Computer Vision (ACCV) 2020 , Best Paper Honorable Mention Award

Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh
Project PagePDFCodeVideo

Image

3D-Aware Scene Change Captioning from Multiview Images

In IEEE Robotics and Automation Letters (RA-L) with IROS presentation 2020

Yue Qiu, Yutaka Satoh, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka
PDF

Image

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data

In International Conference on Pattern Recognition (ICPR) 2020

Nakamasa Inoue*, Eisuke Yamagata*, Hirokatsu Kataoka
PDF

Image

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

In International Conference on Pattern Recognition (ICPR) 2020

Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue
PDF

Image

Adversarial Knowledge Distillation for a Compact Generator

In International Conference on Pattern Recognition (ICPR) 2020

Hideki Tsunashima, Shigeo Morishima, Junji Yamato, Qiu Chen, Hirokatsu Kataoka
PDF

Image

Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location

In International Conference on Pattern Recognition (ICPR) 2020

Hiroaki Aizawa, Hirokatsu Kataoka, Yutaka Satoh, Kunihito Kato
Project PagePDF

Image

Retrieving and Highlighting Action with Spatiotemporal Reference

In IEEE International Conference on Image Processing (ICIP) 2020

Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka
PDF

Image

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

In arXiv 2020

Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh
PDFCode

Image

Weakly Supervised Dataset Collection for Robust Person Detection

In arXiv 2020

Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka
PDFCode

Image

Joint Pedestrian Detection and Risk-level Prediction with Motion-Representation-by-Detection

In International Conference on Robotics and Automation (ICRA) 2020

Hirokatsu Kataoka, Teppei Suzuki, Kodai Nakashima, Yutaka Satoh, Yoshimitsu Aoki
PDF

Image

Joking AI via Visual Cues

In Human Computer Interaction International (HCI) 2020

Ryota Suzuki, Kota Yoshida, Munetaka Minoguchi, Kazuki Tsubura, Takumu Ikeya, Akio Nakamura, Hirokatsu Kataoka
PDF

Image

What Do Adversarially Robust Models Look At?

In arXiv 2019

Takahiro Itazuri*, Yoshihiro Fukuhara*, Hirokatsu Kataoka, Shigeo Morishima
PDF

Image

Incorporating 3D Information Into Visual Question Answering

In International Conference on 3D Vision (3DV) 2019

Yue Qiu, Yutaka Satoh, Ryota Suzuki, Hirokatsu Kataoka
PDF

Image

Visual Question Answering with RGB-D Images

In CVPR 2019 Workshop on Women in Computer Vision (WiCV) 2019

Yue Qiu, Yutaka Satoh, Hirokatsu Kataoka, Ryota Suzuki

Image

Ten-million-order Human Database for World-wide Fashion Culture Analysis

In CVPR 2019 Workshop on Understanding Subjective Attributes of Data, Focus on Fashion and Subjective Search (FFSS-USAD) 2019

Hirokatsu Kataoka, Kaori Abe, Munetaka Minoguchi, Akio Nakamura, Yutaka Satoh
PDFCode

Image

Unsupervised Out-of-context Action Understanding

In IEEE International Conference on Robotics and Automation (ICRA) 2019

Hirokatsu Kataoka, Yutaka Satoh
PDF