1 code implementation • 17 Dec 2023 • Shota Nishiyama, Takuma Saito, Ryo Nakamura, Go Ohtani, Hirokatsu Kataoka, Kensho Hara
Our proposed dataset aims to improve the performance of traffic accident recognition by annotating ten types of environmental information as teacher labels in addition to the presence or absence of traffic accidents.
no code implementations • 26 Sep 2023 • Guoqing Hao, Satoshi Iizuka, Kensho Hara, Edgar Simo-Serra, Hirokatsu Kataoka, Kazuhiro Fukui
We present a novel framework for rectifying occlusions and distortions in degraded texture samples from natural images.
no code implementations • 8 Aug 2023 • Tomoki Arai, Kenji Iwata, Kensho Hara, Yutaka Satoh
Drones are being used to assess the situation in various disasters.
no code implementations • Smart Agricultural Technology 2023 • Risa Shinoda, Ko Motoki, Kensho Hara, Hirokatsu Kataoka, Ryohei Nakano, Tetsuya Nakazaki, Ryozo Noguchi
The RoseBlooming dataset is the innovative dataset of labeled images for cut flowers at the growing stage.
1 code implementation • 19 May 2020 • Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods.
10 code implementations • 10 Apr 2020 • Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh
Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy.
26 code implementations • CVPR 2018 • Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh
The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels.
Ranked #49 on Action Recognition on UCF101
1 code implementation • 25 Aug 2017 • Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh
The 3D ResNets trained on the Kinetics did not suffer from overfitting despite the large number of parameters of the model, and achieved better performance than relatively shallow networks, such as C3D.