Search Results for author: Masakazu Iwamura

Found 9 papers, 1 papers with code

Word-level Sign Language Recognition with Multi-stream Neural Networks Focusing on Local Regions

no code implementations30 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)

Sign Language Recognition

Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images

no code implementations28 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.

Data Augmentation Object Counting

Advances of Scene Text Datasets

no code implementations13 Dec 2018 Masakazu Iwamura

This article introduces publicly available datasets in scene text detection and recognition.

Scene Text Detection Text Detection

ShakeDrop Regularization for Deep Residual Learning

5 code implementations7 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.

ShakeDrop regularization

no code implementations ICLR 2018 Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise

This paper proposes a powerful regularization method named \textit{ShakeDrop regularization}.

Deep Pyramidal Residual Networks with Separated Stochastic Depth

no code implementations5 Dec 2016 Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise

On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy.

Object Recognition

A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents

no code implementations4 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.

Optical Character Recognition (OCR)

Scalable Solution for Approximate Nearest Subspace Search

no code implementations29 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.