716 citations · 825 across the 31 of their papers we have counts for
34 papers
Multi-source Transfer Learning of Time Series with a Shapelet-based Distance Measure
Jiseok Lee, Brian Kenji Iwana
Transfer learning is an effective technique for addressing data scarcity in deep learning for time series classification, but its success depends on the selection of source dataset…
Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing
Yataro Tamura, Brian Kenji Iwana, Jiseok Lee
Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversari…
Domain Adaptation for Ulcerative Colitis Severity Estimation Using Patient-Level Diagnoses
Takamasa Yamaguchi, Brian Kenji Iwana, Ryoma Bise +4
The development of methods to estimate the severity of Ulcerative Colitis (UC) is of significant importance. However, these methods often suffer from domain shifts caused by differ…
Towards Time Series Generation Conditioned on Unstructured Natural Language
Jaeyun Woo, Jiseok Lee, Brian Kenji Iwana
Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant a…
Model Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification
Jiseok Lee, Brian Kenji Iwana
Transfer learning is a common practice that alleviates the need for extensive data to train neural networks. It is performed by pre-training a model using a source dataset and fine…
What Text Design Characterizes Book Genres?
Daichi Haraguchi, Brian Kenji Iwana, Seiichi Uchida
This study analyzes the relationship between non-verbal information (e.g., genres) and text design (e.g., font style, character color, etc.) through the classification of book genr…
Few shot font generation via transferring similarity guided global style and quantization local style
Wei Pan, Anna Zhu, Xinyu Zhou +2
Automatic few-shot font generation (AFFG), aiming at generating new fonts with only a few glyph references, reduces the labor cost of manually designing fonts. However, the traditi…
Deep Attentive Time Warping
Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan +4
Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used…
FETNet: Feature Erasing and Transferring Network for Scene Text Removal
Guangtao Lyu, Kun Liu, Anna Zhu +2
The scene text removal (STR) task aims to remove text regions and recover the background smoothly in images for private information protection. Most existing STR methods adopt enco…
Vision Conformer: Incorporating Convolutions into Vision Transformer Layers
Brian Kenji Iwana, Akihiro Kusuda
Transformers are popular neural network models that use layers of self-attention and fully-connected nodes with embedded tokens. Vision Transformers (ViT) adapt transformers for im…
Contour Completion by Transformers and Its Application to Vector Font Data
Yusuke Nagata, Brian Kenji Iwana, Seiichi Uchida
In documents and graphics, contours are a popular format to describe specific shapes. For example, in the True Type Font (TTF) file format, contours describe vector outlines of typ…
On Mini-Batch Training with Varying Length Time Series
Brian Kenji Iwana
In real-world time series recognition applications, it is possible to have data with varying length patterns. However, when using artificial neural networks (ANN), it is standard p…
Dynamic Data Augmentation with Gating Networks for Time Series Recognition
Daisuke Oba, Shinnosuke Matsuo, Brian Kenji Iwana
Data augmentation is a technique to improve the generalization ability of machine learning methods by increasing the size of the dataset. However, since every augmentation method i…
Using Robust Regression to Find Font Usage Trends
Kaigen Tsuji, Seiichi Uchida, Brian Kenji Iwana
Fonts have had trends throughout their history, not only in when they were invented but also in their usage and popularity. In this paper, we attempt to specifically find the trend…
Towards Book Cover Design via Layout Graphs
Wensheng Zhang, Yan Zheng, Taiga Miyazono +2
Book covers are intentionally designed and provide an introduction to a book. However, they typically require professional skills to design and produce the cover images. Thus, we p…
Font Style that Fits an Image -- Font Generation Based on Image Context
Taiga Miyazono, Brian Kenji Iwana, Daichi Haraguchi +1
When fonts are used on documents, they are intentionally selected by designers. For example, when designing a book cover, the typography of the text is an important factor in the o…
Self-Augmented Multi-Modal Feature Embedding
Shinnosuke Matsuo, Seiichi Uchida, Brian Kenji Iwana
Oftentimes, patterns can be represented through different modalities. For example, leaf data can be in the form of images or contours. Handwritten characters can also be either onl…
Attention to Warp: Deep Metric Learning for Multivariate Time Series
Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan +4
Deep time series metric learning is challenging due to the difficult trade-off between temporal invariance to nonlinear distortion and discriminative power in identifying non-match…
What is the Reward for Handwriting? -- Handwriting Generation by Imitation Learning
Keisuke Kanda, Brian Kenji Iwana, Seiichi Uchida
Analyzing the handwriting generation process is an important issue and has been tackled by various generation models, such as kinematics based models and stochastic models. In this…
Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathology
Hiroki Tokunaga, Brian Kenji Iwana, Yuki Teramoto +2
We propose a weakly-supervised cell tracking method that can train a convolutional neural network (CNN) by using only the annotation of "cell detection" (i.e., the coordinates of c…
An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
Brian Kenji Iwana, Seiichi Uchida
In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase…
On the Ability of a CNN to Realize Image-to-Image Language Conversion
Kohei Baba, Seiichi Uchida, Brian Kenji Iwana
The purpose of this paper is to reveal the ability that Convolutional Neural Networks (CNN) have on the novel task of image-to-image language conversion. We propose a new network t…
Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
Brian Kenji Iwana, Seiichi Uchida
Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time…
Effect of Text Color on Word Embeddings
Masaya Ikoma, Brian Kenji Iwana, Seiichi Uchida
In natural scenes and documents, we can find the correlation between a text and its color. For instance, the word, "hot", is often printed in red, while "cold" is often in blue. Th…