collaborators

6 papers

cs.CV2025

FoodLogAthl-218: Constructing a Real-World Food Image Dataset Using Dietary Management Applications

Mitsuki Watanabe, Sosuke Amano, Kiyoharu Aizawa +1

Food image classification models are crucial for dietary management applications because they reduce the burden of manual meal logging. However, most publicly available datasets fo…

cs.MM2025

360CityGML: Realistic and Interactive Urban Visualization System Integrating CityGML Model and 360° Videos

Tatsuro Banno, Mizuki Takenawa, Leslie Wöhler +2

We introduce a novel urban visualization system that integrates 3D urban model (CityGML) and 360° walkthrough videos. By aligning the videos with the model and dynamically project…

cs.MM2025

Building and Evaluating a Realistic Virtual World for Large Scale Urban Exploration from 360° Videos

Mizuki Takenawa, Naoki Sugimoto, Leslie Wöhler +2

We propose to build realistic virtual worlds, called 360RVW, for large urban environments directly from 360° videos. We provide an interface for interactive exploration, where use…

cs.CV2025

PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization

Haruka Kumagai, Leslie Wöhler, Satoshi Ikehata +1

In response to rising societal awareness of privacy concerns, face anonymization techniques have advanced, including the emergence of face-swapping methods that replace one identit…

cs.MM2025

A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task

Mashiro Toyooka, Kiyoharu Aizawa, Yoko Yamakata

Large Language Models (LLMs) are trained on a vast amount of procedural texts, but they do not directly observe real-world phenomena. In the context of cooking recipes, this poses…

cs.CV2025

FoodMLLM-JP: Leveraging Multimodal Large Language Models for Japanese Recipe Generation

Yuki Imajuku, Yoko Yamakata, Kiyoharu Aizawa

Research on food image understanding using recipe data has been a long-standing focus due to the diversity and complexity of the data. Moreover, food is inextricably linked to peop…