Learn to See Faster: Pushing the Limits of High-Speed Camera with Deep Underexposed Image Denoising

no code implementations • 29 Nov 2022 • Weihao Zhuang, Tristan Hascoet, Ryoichi Takashima, Tetsuya Takiguchi

The ability to record high-fidelity videos at high acquisition rates is central to the study of fast moving phenomena.

Image Denoising Specificity

Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolation

no code implementations • 22 Jun 2022 • Weihao Zhuang, Tristan Hascoet, Ryoichi Takashima, Tetsuya Takiguchi

Recent works have shown the ability of Implicit Neural Representations (INR) to carry meaningful representations of signal derivatives.

Optical Flow Estimation Video Compression +1

Current Source Localization Using Deep Prior with Depth Weighting

no code implementations • 26 Mar 2022 • Rio Yamana, Hajime Yano, Ryoichi Takashima, Tetsuya Takiguchi, Seiji Nakagawa

This paper proposes a novel neuronal current source localization method based on Deep Prior that represents a more complicated prior distribution of current source using convolutional networks.

FasterRCNN Monitoring of Road Damages: Competition and Deployment

2 code implementations • 22 Oct 2020 • Hascoet Tristan, Yihao Zhang, Persch Andreas, Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki

Maintaining aging infrastructure is a challenge currently faced by local and national administrators all around the world.

Road Damage Detection

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition

no code implementations • 26 Jun 2019 • Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2