Search Results for author:
Found 78 papers, 26 papers with code
Pseudo-label Learning with Calibrated Confidence Using an Energy-based Model
In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate confidence is important for successful PL.
Total Disentanglement of Font Images into Style and Character Class Features
Second, it is demonstrated that the disentangled features produced by total disentanglement apply to a variety of tasks, including font recognition, character recognition, and one-shot font image generation.
NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging
The current layout-aware text-to-image diffusion models still have several issues, including mismatches between the text and layout conditions and quality degradation of generated images.
Cross-Domain Image Conversion by CycleDM
By applying machine-printed and handwritten character images to the two modalities, CycleDM realizes the conversion between them.
An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levels
Diffusion models have recently been used for medical image generation because of their high image quality.
Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts
However, the correlation between fonts and their impression is weak and unstable because impressions are subjective.
What Text Design Characterizes Book Genres?
In the experiment, we found that semantic information is sufficient to determine the genre; however, text design is helpful in adding more discriminative features for book genres.
Font Impression Estimation in the Wild
To realize stable impression estimation even with such a dataset, we propose an exemplar-based impression estimation approach, which relies on a strategy of ensembling impressions of exemplar fonts that are similar to the input image.
Font Style Interpolation with Diffusion Models
In this paper, we employ diffusion models to generate new font styles by interpolating a pair of reference fonts with different styles.
Learning to Kern -- Set-wise Estimation of Optimal Letter Space
Kerning is the task of setting appropriate horizontal spaces for all possible letter pairs of a certain font.
Typographic Text Generation with Off-the-Shelf Diffusion Model
The proposed system is a novel combination of two off-the-shelf methods for diffusion models, ControlNet and Blended Latent Diffusion.
Boosting for Bounding the Worst-class Error
This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes.
Local Style Awareness of Font Images
This paper proposes an attention mechanism to find important local parts.
Deep Attentive Time Warping
Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task.
Towards Diverse and Consistent Typography Generation
In this work, we consider the typography generation task that aims at producing diverse typographic styling for the given graphic document.
Selective Scene Text Removal
Scene text removal (STR) is the image transformation task to remove text regions in scene images.
Ambigram Generation by A Diffusion Model
For example, the pair of 'A' and 'V' shows a high ambigramability (that is, it is easy to generate their ambigrams), and the pair of 'D' and 'K' shows a lower ambigramability.
Analyzing Font Style Usage and Contextual Factors in Real Images
There are various font styles in the world.
FETNet: Feature Erasing and Transferring Network for Scene Text Removal
To tackle these problems, we propose a novel Feature Erasing and Transferring (FET) mechanism to reconfigure the encoded features for STR in this paper.
Contour Completion by Transformers and Its Application to Vector Font Data
We propose a Transformer-based method to solve this problem and show the results of the typeface contour completion.
Functional Knowledge Transfer with Self-supervised Representation Learning
This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer.
Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the target domain.
Disease Severity Regression with Continuous Data Augmentation
We propose continuous DA as a solution to the two issues.
Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
This paper proposes a novel and efficient method for Learning from Label Proportions (LLP), whose goal is to train a classifier only by using the class label proportions of instance sets, called bags.
Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification
This work presents a novel self-supervised representation learning method to learn efficient representations without labels on images from a 3DPM sensor (3-Dimensional Particle Measurement; estimates the particle size distribution of material) utilizing RGB images and depth maps of mining material on the conveyor belt.
Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data
This paper proposes a deep Bayesian active-learning-to-rank, which trains a Bayesian convolutional neural network while automatically selecting appropriate pairs for relative annotation.
MontageGAN: Generation and Assembly of Multiple Components by GANs
A multi-layer image is more valuable than a single-layer image from a graphic designer's perspective.
Font Generation with Missing Impression Labels
Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels.
Optimal Rejection Function Meets Character Recognition Tasks
The highlights of LwR are: (1) the rejection strategy is not heuristic but has a strong background from a machine learning theory, and (2) the rejection function can be trained on an arbitrary feature space which is different from the feature space for classification.
Revealing Reliable Signatures by Learning Top-Rank Pairs
Signature verification, as a crucial practical documentation analysis task, has been continuously studied by researchers in machine learning and pattern recognition fields.
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 efficient representations without labels on histopathology medical images utilizing magnification factors.
Ranked #1 on
Breast Cancer Histology Image Classification
on BreakHis
(Accuracy (Inter-Patient) metric)
Breast Cancer Histology Image Classification (20% labels)
Classification Of Breast Cancer Histology Images
+2
Font Shape-to-Impression Translation
The versatility of Transformer allows us to realize two very different approaches for the analysis, i. e., multi-label classification and translation.
TrueType Transformer: Character and Font Style Recognition in Outline Format
The outline format, such as TrueType, represents each character as a sequence of control points of stroke contours and is frequently used in born-digital documents.
Order-Guided Disentangled Representation Learning for Ulcerative Colitis Classification with Limited Labels
Ulcerative colitis (UC) classification, which is an important task for endoscopic diagnosis, involves two main difficulties.
Using Robust Regression to Find Font Usage Trends
In this paper, we attempt to specifically find the trends in font usage using robust regression on a large collection of text images.
Towards Book Cover Design via Layout Graphs
Book covers are intentionally designed and provide an introduction to a book.
Font Style that Fits an Image -- Font Generation Based on Image Context
We propose an end-to-end neural network that inputs the book cover, a target location mask, and a desired book title and outputs stylized text suitable for the cover.
Ranked #1 on
Font Generation
on Book Cover Dataset
Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo
Various findings include the weak positive correlation between the text area ratio and the number of followers of the company.
Attention to Warp: Deep Metric Learning for Multivariate Time Series
This approach adapts a parameterized attention model to time warping for greater and more adaptive temporal invariance.
Which Parts Determine the Impression of the Font?
Various fonts give different impressions, such as legible, rough, and comic-text. This paper aims to analyze the correlation between the local shapes, or parts, and the impression of fonts.
Shared Latent Space of Font Shapes and Their Noisy Impressions
The difficulty is that the impression words attached to a font are often very noisy.
Impressions2Font: Generating Fonts by Specifying Impressions
Various fonts give us various impressions, which are often represented by words.
Meta-learning of Pooling Layers for Character Recognition
As part of our framework, a parameterized pooling layer is proposed in which the kernel shape and pooling operation are trainable using two parameters, thereby allowing flexible pooling of the input data.
Self-Augmented Multi-Modal Feature Embedding
To exploit this fact, we propose the use of self-augmentation and combine it with multi-modal feature embedding.
Layer-Wise Interpretation of Deep Neural Networks Using Identity Initialization
The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning.
Handwriting Prediction Considering Inter-Class Bifurcation Structures
In this paper, we propose a temporal prediction model that can deal with this bifurcation structure.
What is the Reward for Handwriting? -- Handwriting Generation by Imitation Learning
In this study, we use a reinforcement learning (RL) framework to realize handwriting generation with the careful future planning ability.
AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee
For visual object tracking, it is difficult to realize an almighty online tracker due to the huge variations of target appearance depending on an image sequence.
Ranked #1 on
Visual Object Tracking
on TempleColor128
An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks.
Label or Message: A Large-Scale Experimental Survey of Texts and Objects Co-Occurrence
Our daily life is surrounded by textual information.
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 Neural Networks (CNN) have on the novel task of image-to-image language conversion.
Lyric Video Analysis Using Text Detection and Tracking
In order to analyze the motion of lyric words, we first apply a state-of-the-art scene text detector and recognizer to each video frame.
Guided neural style transfer for shape stylization
Designing logos, typefaces, and other decorated shapes can require professional skills.
Regularized Pooling
This means that max pooling is too flexible to compensate for actual deformations.
Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
In order to address this problem, we propose a novel time series data augmentation called guided warping.
Effect of Text Color on Word Embeddings
In natural scenes and documents, we can find the correlation between a text and its color.
Iconify: Converting Photographs into Icons
In this paper, we tackle a challenging domain conversion task between photo and icon images.
Character-independent font identification
Moreover, we analyzed the relationship between character classes and font identification accuracy.
Neural Style Difference Transfer and Its Application to Font Generation
In our proposed method, the difference of font styles between two different fonts is found and transferred to another font using neural style transfer.
A Discriminative Gaussian Mixture Model with Sparsity
We propose a sparse classifier based on a discriminative GMM, referred to as a sparse discriminative Gaussian mixture (SDGM).
SDGM: Sparse Bayesian Classifier Based on a Discriminative Gaussian Mixture Model
In the SDGM, a GMM-based discriminative model is trained by sparse Bayesian learning.
Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
Through qualitative and quantitative analysis, we demonstrate that SGLRP can successfully localize and attribute the regions on input images which contribute to a target object's classification.
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 covers and online advertisements.
Scene Text Magnifier
In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, character magnify, and image synthesis.
Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders
This research attempts to construct a network that can convert online and offline handwritten characters to each other.
A Trainable Multiplication Layer for Auto-correlation and Co-occurrence Extraction
In this paper, we propose a trainable multiplication layer (TML) for a neural network that can be used to calculate the multiplication between the input features.
GlyphGAN: Style-Consistent Font Generation Based on Generative Adversarial Networks
In GlyphGAN, the input vector for the generator network consists of two vectors: character class vector and style vector.
ProbAct: A Probabilistic Activation Function for Deep Neural Networks
We show that ProbAct increases the classification accuracy by +2-3% compared to ReLU or other conventional activation functions on both original datasets and when datasets are reduced to 50% and 25% of the original size.
Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networks
GAN-based generative models only learn the projection between a random distribution as input data and the distribution of training data. Therefore, the relationship between input and generated data is unclear, and the characteristics of the data generated from this model cannot be controlled.
How do Convolutional Neural Networks Learn Design?
We use LRP to explain the pixel-wise contributions of book cover design and highlight the design elements contributing towards particular genres.
Constrained Neural Style Transfer for Decorated Logo Generation
We propose using neural style transfer with clip art and text for the creation of new and genuine logos.
Dynamic Weight Alignment for Temporal Convolutional Neural Networks
In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming.
CNN training with graph-based sample preselection: application to handwritten character recognition
In this paper, we present a study on sample preselection in large training data set for CNN-based classification.
Scene Text Eraser
That proves the effectiveness of proposed method for erasing the text in natural scene images.
Automatic Generation of Typographic Font from a Small Font Subset
The proposed method uses strokes from given samples for font generation.
Globally Optimal Object Tracking with Fully Convolutional Networks
Thus, we propose a new and robust tracking method using a Fully Convolutional Network (FCN) to obtain an object probability map and Dynamic Programming (DP) to seek the globally optimal path through all frames of video.
Judging a Book By its Cover
Book covers communicate information to potential readers, but can that same information be learned by computers?
Ranked #1 on
Genre classification
on Book Cover Dataset
