Publications

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

Pre-training without Natural Images

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

Asian Conference on Computer Vision (ACCV), 2020

[Paper] [GitHub]

Retrieving and Highlighting Action with Spatiotemporal Reference

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

IEEE International Conference on Image Processing (ICIP), 2020

[Paper]

Alleviating Over-segmentation Errors by Detecting Action Boundaries

Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka

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

[Paper] [GitHub]

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

Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh

arXiv Preprint

[Paper] [GitHub]

Weakly Supervised Dataset Collection for Robust Person Detection

Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka

arXiv Preprint

[Paper] [GitHub]

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

Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue

arXiv Preprint

[Paper]

Joking AI via Visual cues

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

HCI International, 2020

Visual Question Answering with RGB-D Images

Yue Qiu, Yutaka Satoh, Hirokatsu Kataoka, Ryota Suzuki

CVPR Workshop on Women in Computer Vision, 2019

[Paper]

Incorporating Depth into Visual Question Answering

Yue Qiu, Yutaka Satoh, Hirokatsu Kataoka, Ryota Suzuki

CVPR Workshop on Visual Question Answering and Dialog, 2019

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

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

CVPR Workshop on Understanding Subjective Attributes of Data, 2019

[Paper]

Unsupervised Out-of-context Action Understanding

Hirokatsu Kataoka, Yutaka Satoh

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

[Paper]

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB

Tomoyuki Suzuki*, Hirokatsu Kataoka*, Yoshimitsu Aoki, Yutaka Satoh

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

[Paper]

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

[Paper] [GitHub]

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents

Hirokatsu Kataoka, Teppei Suzuki, Shoko Oikawa, Yasuhiro Matsui, Yutaka Satoh

IEEE International Conference on Robotics and Automation (ICRA), 2018

[Paper]