Kent Fujiwara


I am a research scientist at LY Corporation. My research interests is in computer vision, mainly dealing with point cloud analysis, 3D vision, image registration and 3D reconstruction. Along with my colleagues I lead a lab called Virtual Human Laboratory between LY Corporation and Osaka University.

News: We have one paper accepted to ECCV 2024! Stay tuned for more details.

Bio CV Mail Twitter (en) Twitter (jp) Scholar Github LinkedIn

Profile picture

Publications

Project image
Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models
Kent Fujiwara, Mikihiro Tanaka, Qing Yu
Proc. of the European Conf. on Computer Vision (ECCV), 2024
Project Page / Paper /
@InProceedings{Fujiwara_2024_ECCV, 
	author = {Kent Fujiwara and Mikihiro Tanaka and Qing Yu}, 
	title = {Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models}, 
	booktitle = {Proc. of the European Conf. on Computer Vision (ECCV)}, 
	year = {2024}, 
}
Project image
Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches
Qing Yu, Mikihiro Tanaka, Kent Fujiwara
Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2024
Project Page / Paper /
@InProceedings{Yu_2024_CVPR, 
	author = {Qing Yu and Mikihiro Tanaka and Kent Fujiwara}, 
	title = {Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches}, 
	booktitle = {Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2024}, 
}
Project image
Role-Aware Interaction Generation from Textual Description (Oral Presentation)
Mikihiro Tanaka, Kent Fujiwara
Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV), 2023
Project Page / Paper /
@InProceedings{Tanaka_2023_ICCV, 
	author = {Mikihiro Tanaka and Kent Fujiwara}, 
	title = {Role-Aware Interaction Generation from Textual Description}, 
	booktitle = {Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV)}, 
	year = {2023}, 
}
Project image
Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Temporal Action Localization (Oral Presentation)
Qing Yu, Kent Fujiwara
Proc. of the AAAI Conf. on Artificial Intelligenc (AAAI), 2023
Project Page / Paper /
@InProceedings{yu2023swtal, 
	author = {Qing Yu and Kent Fujiwara}, 
	title = {Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Temporal Action Localization}, 
	booktitle = {Proc. of the AAAI Conf. on Artificial Intelligenc (AAAI)}, 
	year = {2023}, 
}
Project image
Generalized Shuffled Linear Regression with Outliers in Both Covariates and Responses
Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita
International Journal of Computer Vision (IJCV), 2022
Project Page / Paper /
@InProceedings{li2022jgslr, 
	author = {Feiran Li and Kent Fujiwara and Fumio Okura and Yasuyuki Matsushita}, 
	title = {Generalized Shuffled Linear Regression with Outliers in Both Covariates and Responses}, 
	booktitle = {International Journal of Computer Vision (IJCV)}, 
	year = {2022}, 
}
Project image
Generalized Shuffled Linear Regression (Oral Presentation)
Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita
Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV), 2021
Project Page / Paper /
@InProceedings{li2021gslr, 
	author = {Feiran Li and Kent Fujiwara and Fumio Okura and Yasuyuki Matsushita}, 
	title = {Generalized Shuffled Linear Regression}, 
	booktitle = {Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV)}, 
	year = {2021}, 
}
Project image
A Closer Look at Rotation-invariant Deep Point Cloud Analysis
Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita
Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV), 2021
Project Page / Paper /
@InProceedings{li2021rotinv, 
	author = {Feiran Li and Kent Fujiwara and Fumio Okura and Yasuyuki Matsushita}, 
	title = {A Closer Look at Rotation-invariant Deep Point Cloud Analysis}, 
	booktitle = {Proc. of the IEEE/CVF International Conf. on Computer Vision (ICCV)}, 
	year = {2021}, 
}
Project image
Toward a Unified Framework for Point Set Registration
Feiran Li, Kent Fujiwara, Yasuyuki Matsushita
Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2021
Project Page / Paper /
@InProceedings{li2021toward, 
	author = {Feiran Li and Kent Fujiwara and Yasuyuki Matsushita}, 
	title = {Toward a Unified Framework for Point Set Registration}, 
	booktitle = {Proc. of the IEEE International Conference on Robotics and Automation (ICRA)}, 
	year = {2021}, 
}
Project image
Neural Implicit Embedding for Point Cloud Analysis
Kent Fujiwara, Taiichi Hashimoto
Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2020
Project Page / Paper /
@InProceedings{fujiwara2020neural, 
	author = {Kent Fujiwara and Taiichi Hashimoto}, 
	title = {Neural Implicit Embedding for Point Cloud Analysis}, 
	booktitle = {Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)}, 
	year = {2020}, 
}
Project image
Canonical and Compact Point Cloud Representation for Shape Classification
Kent Fujiwara, Ikuro Sato, Mitsuru Ambai, Yuichi Yoshida, Yoshiaki Sakakura
arXiv.org, 2018
Project Page / Paper /
@InProceedings{fujiwara2018canonical, 
	author = {Kent Fujiwara and Ikuro Sato and Mitsuru Ambai and Yuichi Yoshida and Yoshiaki Sakakura}, 
	title = {Canonical and Compact Point Cloud Representation for Shape Classification}, 
	booktitle = {arXiv.org}, 
	year = {2018}, 
}
Project image
Unsupervised Categorical Shape Reconstruction Through Manifolds
Kent Fujiwara, Minoru Mori, Kunio Kashino
IEEE Winter Conference on Applications of Computer Vision (WACV), 2016
Project Page / Paper /
@InProceedings{fujiwara2016unsupervised, 
	author = {Kent Fujiwara and Minoru Mori and Kunio Kashino}, 
	title = {Unsupervised Categorical Shape Reconstruction Through Manifolds}, 
	booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)}, 
	year = {2016}, 
}
Project image
Non-rigid Registration with Reliable Distance Field for Dynamic Shape Completion
Kent Fujiwara, Hiroshi Kawasaki, Ryusuke Sagawa, Koichi Ogawara, Katsushi Ikeuchi
3DV Workshop on Dynamic Shape Measurement and Analysis, 2014
Project Page / Paper /
@InProceedings{fujiwara2014non, 
	author = {Kent Fujiwara and Hiroshi Kawasaki and Ryusuke Sagawa and Koichi Ogawara and Katsushi Ikeuchi}, 
	title = {Non-rigid Registration with Reliable Distance Field for Dynamic Shape Completion}, 
	booktitle = {3DV Workshop on Dynamic Shape Measurement and Analysis}, 
	year = {2014}, 
}
Project image
Locally rigid globally non-rigid surface registration
Kent Fujiwara, Ko Nishino, Jun Takamatsu, Bo Zheng, Katsushi Ikeuchi
Proc. of the IEEE International Conf. on Computer Vision (ICCV), 2011
Project Page / Paper /
@InProceedings{fujiwara2011locally, 
	author = {Kent Fujiwara and Ko Nishino and Jun Takamatsu and Bo Zheng and Katsushi Ikeuchi}, 
	title = {Locally rigid globally non-rigid surface registration}, 
	booktitle = {Proc. of the IEEE International Conf. on Computer Vision (ICCV)}, 
	year = {2011}, 
}

Talks

Template from Michael Niemeyer's page.