Seiichi Uchida

research

∙ 09/13/2023

Deep Attentive Time Warping

Similarity measures for time series are important problems for time seri...

0 Shinnosuke Matsuo, et al. ∙

research

∙ 09/05/2023

Towards Diverse and Consistent Typography Generation

In this work, we consider the typography generation task that aims at pr...

0 Wataru Shimoda, et al. ∙

research

∙ 09/04/2023

Toward Defensive Letter Design

A major approach for defending against adversarial attacks aims at contr...

0 Rentaro Kataoka, et al. ∙

research

∙ 09/01/2023

Selective Scene Text Removal

Scene text removal (STR) is the image transformation task to remove text...

0 Hayato Mitani, et al. ∙

research

∙ 06/21/2023

Analyzing Font Style Usage and Contextual Factors in Real Images

There are various font styles in the world. Different styles give differ...

0 Naoya Yasukochi, et al. ∙

research

∙ 06/21/2023

Ambigram Generation by A Diffusion Model

Ambigrams are graphical letter designs that can be read not only from th...

0 Takahiro Shirakawa, et al. ∙

research

∙ 06/16/2023

FETNet: Feature Erasing and Transferring Network for Scene Text Removal

The scene text removal (STR) task aims to remove text regions and recove...

0 Guangtao Lyu, et al. ∙

research

∙ 04/27/2023

Contour Completion by Transformers and Its Application to Vector Font Data

In documents and graphics, contours are a popular format to describe spe...

0 Yusuke Nagata, et al. ∙

research

∙ 03/02/2023

Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification

Semi-supervised domain adaptation is a technique to build a classifier f...

0 Shota Harada, et al. ∙

research

∙ 02/24/2023

Disease Severity Regression with Continuous Data Augmentation

Disease severity regression by a convolutional neural network (CNN) for ...

0 Shumpei Takezaki, et al. ∙

research

∙ 02/17/2023

Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization

This paper proposes a novel and efficient method for Learning from Label...

0 Shinnosuke Matsuo, et al. ∙

research

∙ 10/18/2022

Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification

This work presents a novel self-supervised representation learning metho...

0 Prakash Chandra Chhipa, et al. ∙

research

∙ 08/05/2022

Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data

Automatic image-based disease severity estimation generally uses discret...

0 Takeaki Kadota, et al. ∙

research

∙ 05/31/2022

MontageGAN: Generation and Assembly of Multiple Components by GANs

A multi-layer image is more valuable than a single-layer image from a gr...

0 Chean Fei Shee, et al. ∙

research

∙ 03/19/2022

Font Generation with Missing Impression Labels

Our goal is to generate fonts with specific impressions, by training a g...

0 Seiya Matsuda, et al. ∙

research

∙ 03/17/2022

Revealing Reliable Signatures by Learning Top-Rank Pairs

Signature verification, as a crucial practical documentation analysis ta...

0 Xiaotong Ji, et al. ∙

research

∙ 03/17/2022

Optimal Rejection Function Meets Character Recognition Tasks

In this paper, we propose an optimal rejection method for rejecting ambi...

0 Xiaotong Ji, et al. ∙

research

∙ 03/15/2022

Magnification Prior: A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Images

This work presents a novel self-supervised pre-training method to learn ...

0 Prakash Chandra Chhipa, et al. ∙

research

∙ 03/11/2022

Font Shape-to-Impression Translation

Different fonts have different impressions, such as elegant, scary, and ...

0 Masaya Ueda, et al. ∙

research

∙ 03/10/2022

TrueType Transformer: Character and Font Style Recognition in Outline Format

We propose TrueType Transformer (T3), which can perform character and fo...

0 Yusuke Nagata, et al. ∙

research

∙ 11/06/2021

Order-Guided Disentangled Representation Learning for Ulcerative Colitis Classification with Limited Labels

Ulcerative colitis (UC) classification, which is an important task for e...

0 Shota Harada, et al. ∙

research

∙ 10/05/2021

De-rendering Stylized Texts

Editing raster text is a promising but challenging task. We propose to a...

0 Wataru Shimoda, et al. ∙

research

∙ 06/29/2021

Using Robust Regression to Find Font Usage Trends

Fonts have had trends throughout their history, not only in when they we...

3 Kaigen Tsuji, et al. ∙

research

∙ 05/24/2021

Towards Book Cover Design via Layout Graphs

Book covers are intentionally designed and provide an introduction to a ...

0 Wensheng Zhang, et al. ∙

research

∙ 05/19/2021

Font Style that Fits an Image – Font Generation Based on Image Context

When fonts are used on documents, they are intentionally selected by des...

0 Taiga Miyazono, et al. ∙

research

∙ 04/01/2021

Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo

This paper analyzes a large number of logo images from the LLD-logo data...

0 Shintaro Nishi, et al. ∙

research

∙ 03/28/2021

Attention to Warp: Deep Metric Learning for Multivariate Time Series

Deep time series metric learning is challenging due to the difficult tra...

0 Shinnosuke Matsuo, et al. ∙

research

∙ 03/23/2021

Shared Latent Space of Font Shapes and Impressions

We have specific impressions from the style of a typeface (font), sugges...

0 Jihun Kang, et al. ∙

research

∙ 03/18/2021

Impressions2Font: Generating Fonts by Specifying Impressions

Various fonts give us various impressions, which are often represented b...

0 Seiya Matsuda, et al. ∙

research

∙ 03/17/2021

Meta-learning of Pooling Layers for Character Recognition

In convolutional neural network-based character recognition, pooling lay...

8 Takato Otsuzuki, et al. ∙

research

∙ 03/08/2021

Self-Augmented Multi-Modal Feature Embedding

Oftentimes, patterns can be represented through different modalities. Fo...

0 Shinnosuke Matsuo, et al. ∙

research

∙ 02/26/2021

Layer-Wise Interpretation of Deep Neural Networks Using Identity Initialization

The interpretability of neural networks (NNs) is a challenging but essen...

0 Shohei Kubota, et al. ∙

research

∙ 09/27/2020

Handwriting Prediction Considering Inter-Class Bifurcation Structures

Temporal prediction is a still difficult task due to the chaotic behavio...

0 Masaki Yamagata, et al. ∙

research

∙ 09/23/2020

What is the Reward for Handwriting? – Handwriting Generation by Imitation Learning

Analyzing the handwriting generation process is an important issue and h...

11 Keisuke Kanda, et al. ∙

research

∙ 09/19/2020

AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee

For visual object tracking, it is difficult to realize an almighty onlin...

0 Heon Song, et al. ∙

research

∙ 07/31/2020

An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks

In recent times, deep artificial neural networks have achieved many succ...

0 Brian Kenji Iwana, et al. ∙

research

∙ 07/30/2020

Label or Message: A Large-Scale Experimental Survey of Texts and Objects Co-Occurrence

Our daily life is surrounded by textual information. Nowadays, the autom...

0 Koki Takeshita, et al. ∙

research

∙ 06/22/2020

On the Ability of a CNN to Realize Image-to-Image Language Conversion

The purpose of this paper is to reveal the ability that Convolutional Ne...

0 Kohei Baba, et al. ∙

research

∙ 06/21/2020

Lyric Video Analysis Using Text Detection and Tracking

We attempt to recognize and track lyric words in lyric videos. Lyric vid...

0 Shota Sakaguchi, et al. ∙

research

∙ 05/06/2020

Regularized Pooling

In convolutional neural networks (CNNs), pooling operations play importa...

0 Takato Otsuzuki, et al. ∙

research

∙ 04/19/2020

Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher

Neural networks have become a powerful tool in pattern recognition and p...

0 Brian Kenji Iwana, et al. ∙

research

∙ 04/18/2020

Effect of Text Color on Word Embeddings

In natural scenes and documents, we can find the correlation between a t...

0 Masaya Ikoma, et al. ∙

research

∙ 04/07/2020

Iconify: Converting Photographs into Icons

In this paper, we tackle a challenging domain conversion task between ph...

0 Takuro Karamatsu, et al. ∙

research

∙ 01/24/2020

Character-independent font identification

There are a countless number of fonts with various shapes and styles. In...

8 Daichi Haraguchi, et al. ∙

research

∙ 01/21/2020

Neural Style Difference Transfer and Its Application to Font Generation

Designing fonts requires a great deal of time and effort. It requires pr...

0 Gantugs Atarsaikhan, et al. ∙

research

∙ 11/14/2019

SDGM: Sparse Bayesian Classifier Based on a Discriminative Gaussian Mixture Model

In probabilistic classification, a discriminative model based on Gaussia...

22 Hideaki Hayashi, et al. ∙

research

∙ 08/06/2019

Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation

Convolutional Neural Networks (CNN) have become state-of-the-art in the ...

30 Brian Kenji Iwana, et al. ∙

research

∙ 06/24/2019

Serif or Sans: Visual Font Analytics on Book Covers and Online Advertisements

In this paper, we conduct a large-scale study of font statistics in book...

0 Yuto Shinahara, et al. ∙

research

∙ 06/14/2019

Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders

This research attempts to construct a network that can convert online an...

1 Taichi Sumi, et al. ∙

research

∙ 05/30/2019

A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction

In this paper, we propose a trainable multiplication layer (TML) for a n...

0 Hideaki Hayashi, et al. ∙

Seiichi Uchida

Featured Co-authors