29 citations · 67 across the 17 of their papers we have counts for
18 papers
Where Did the Light Come From? Diagnosing Cast-Shadow Reasoning in VLMs and Borrowing the Missing Shadow Prior from Image Generation Models
Ryugo Morita, Shunsuke Kitada, Stanislav Frolov +5
Shadows are observable consequences of latent physical causes, arising from the interaction between illumination, object geometry, and scene structure. A model that understands sha…
GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers
Takuro Kawada, Shunsuke Kitada, Hitoshi Iyatomi
Graphical Abstracts (GAs) visually summarize the key findings of academic papers, playing a crucial role in facilitating the understanding of research content. Recently, advancemen…
A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
Michito Takeshita, Takuro Kawada, Takumi Ohashi +2
AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-b…
TAUE: Training-free Noise Transplant and Cultivation Diffusion Model
Daichi Nagai, Ryugo Morita, Shunsuke Kitada +1
Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring la…
SciGA: A Comprehensive Dataset for Designing Graphical Abstracts in Academic Papers
Takuro Kawada, Shunsuke Kitada, Sota Nemoto +1
Graphical Abstracts (GAs) play a crucial role in visually conveying the key findings of scientific papers. Although recent research increasingly incorporates visual materials such…
Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
Sota Nemoto, Shunsuke Kitada, Hitoshi Iyatomi
Data imbalance presents a significant challenge in various machine learning (ML) tasks, particularly named entity recognition (NER) within natural language processing (NLP). NER ex…
Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives
Shunsuke Kitada
With the dramatic advances in deep learning technology, machine learning research is focusing on improving the interpretability of model predictions as well as prediction performan…
Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired
Kazuya Ohata, Shunsuke Kitada, Hitoshi Iyatomi
We propose a simple yet effective image captioning framework that can determine the quality of an image and notify the user of the reasons for any flaws in the image. Our framework…
Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents
Tsubasa Nakagawa, Shunsuke Kitada, Hitoshi Iyatomi
It is often difficult to correctly infer a writer's emotion from text exchanged online, and differences in recognition between writers and readers can be problematic. In this paper…
DMS: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
Shunsuke Kitada, Yuki Iwazaki, Riku Togashi +1
There is increasing interest in the use of multimodal data in various web applications, such as digital advertising and e-commerce. Typical methods for extracting important informa…
Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks
Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki
Discontinuing ad creatives at an appropriate time is one of the most important ad operations that can have a significant impact on sales. Such operational support for ineffective a…
Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training
Shunsuke Kitada, Hitoshi Iyatomi
Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and mod…
Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
Takumi Aoki, Shunsuke Kitada, Hitoshi Iyatomi
We propose a new character-based text classification framework for non-alphabetic languages, such as Chinese and Japanese. Our framework consists of a variational character encoder…
Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
Shunsuke Kitada, Hitoshi Iyatomi
Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerabl…
AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss
Mahmoud Daif, Shunsuke Kitada, Hitoshi Iyatomi
Classical and some deep learning techniques for Arabic text classification often depend on complex morphological analysis, word segmentation, and hand-crafted feature engineering.…
Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creative
Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki
Accurately predicting conversions in advertisements is generally a challenging task, because such conversions do not occur frequently. In this paper, we propose a new framework to…
End-to-End Text Classification via Image-based Embedding using Character-level Networks
Shunsuke Kitada, Ryunosuke Kotani, Hitoshi Iyatomi
For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate w…
Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning
Shunsuke Kitada, Hitoshi Iyatomi
In this report, we introduce the outline of our system in Task 3: Disease Classification of ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection. We fine-tuned multiple pre-t…