Research Projects– archive –

Detecting Slang on the Dark Web Based on Word Co-Occurrence Relationships in Anchor Texts Abstract　The dark web is widely used for illegal activities such as drug trafficking and cybercrime, where specialized slang is often employed to conceal criminal intent. We propose a novel method for detecting crime-related s...

NIED: A Corpus for Numeric Information Extraction from Dataset Descriptions Abstract: Although a large number of machine learning datasets have been proposed, their descriptions are often insufficiently structured, making it difficult to search datasets using quantitative criteria. To address this issue, we construc...

Illustrated Character Face Super-Deformation via Unsupervised Image-to-Image Translation Abstract:　In this study, we introduce a new image generation task: the super-deformation of character images. We　propose a GAN-based training method that does not require paired data. Experimental results demonstrate that our ...

Quality assessment of synthetic images via spatial distortion recognition Abstract　Generative adversarial networks (GANs) trained on limited data often produce images with spatial distortions. In this study, we propose an efficient method for evaluating the quality of GAN-generated images by training a quality asse...

Investigating Industry–Academia Collaboration in Artificial Intelligence: PDF-Based Bibliometric Analysis from Leading Conferences Abstract: To investigate trends in industry–academia collaboration within the field of artificial intelligence (AI), we conducted a bibliometric analysis of papers presented at...

MambaPainter: Neural Stroke-Based Rendering in a Single Step Abstract:　Stroke-based rendering is a technique that transforms an input image into an oil-painting style by predicting a sequence of brush strokes. However, conventional methods typically predict strokes one by one, resulting in slow processing and limit...

Illustrated Character Face Super-Deformation via Unsupervised Image-to-Image Translation Abstract:　In this study, we introduce a novel image generation task: the super-deformation of character images. We also propose a GAN training framework that does not require paired supervision. Experimental results confirm tha...

Effective Language Representations for Danmaku Comment Classification in Nicovideos Abstract　On video-sharing platforms such as Nicovideo, the danmaku-style commenting system has gained popularity. However, comments that are unrelated to the video can degrade the quality of the information provided. In this study, ...

SolutionTailor: Scientific paper recommendation based on fine-grained abstract analysis Abstract: 　We developed a recommendation system that identifies papers proposing different solutions while sharing the same research objective. The system requires users to specify only the target research field and the abstract...

Finding the Relevance Between Publication Venues Based on Research Trend Similarity and Citation Relationships Abstract: We propose a tool for discovering relationships between conferences and journals across different research fields. When a user inputs the name of a publication venue relevant to their research are...