no code implementations • 30 Jun 2021 • Mizuki Maruyama, Shuvozit Ghose, Katsufumi Inoue, Partha Pratim Roy, Masakazu Iwamura, Michifumi Yoshioka
Thus in this work, we utilized local region images of both hands and face, along with skeletal information to capture local information and the positions of both hands relative to the body, respectively.
Ranked #2 on Sign Language Recognition on WLASL100 (using extra training data)
no code implementations • 28 Aug 2020 • Ryota Akai, Yuzuko Utsumi, Yuka Miwa, Masakazu Iwamura, Koichi Kise
Because conventional object counting methods cannot handle the distortion of omnidirectional images, we propose to process them using stereographic projection, which enables conventional methods to obtain a good approximation of the density function.
no code implementations • 13 Dec 2018 • Masakazu Iwamura
This article introduces publicly available datasets in scene text detection and recognition.
5 code implementations • 7 Feb 2018 • Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba, Koichi Kise
In this paper, to relieve the overfitting effect of ResNet and its improvements (i. e., Wide ResNet, PyramidNet, and ResNeXt), we propose a new regularization method called ShakeDrop regularization.
no code implementations • ICLR 2018 • Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
This paper proposes a powerful regularization method named \textit{ShakeDrop regularization}.
no code implementations • 20 Jan 2017 • Tomo Miyazaki, Tatsunori Tsuchiya, Yoshihiro Sugaya, Shinichiro Omachi, Masakazu Iwamura, Seiichi Uchida, Koichi Kise
The proposed method uses strokes from given samples for font generation.
no code implementations • 5 Dec 2016 • Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy.
no code implementations • 4 May 2016 • Sheraz Ahmed, Muhammad Imran Malik, Muhammad Zeshan Afzal, Koichi Kise, Masakazu Iwamura, Andreas Dengel, Marcus Liwicki
The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e. g., English, Russian, Arabic, Urdu, etc.
no code implementations • 29 Mar 2016 • Masakazu Iwamura, Masataka Konishi, Koichi Kise
The existing methods for the problem are, however, useless in a large-scale problem with a large number of subspaces and high dimensionality of the feature space.