This work addresses the scarcity of high-quality, large-scale resources for Japanese Vision-and-Language (V&L) modeling. We present a scalable and reproducible pipeline that integrates large-scale web collection with rigorous filtering/deduplication, object-detection-driven evidence extraction, and Large Language Model (LLM)-based refinement under grounding constraints. Using this pipeline, we build two resources: an image-caption dataset (DEJIMA-Cap) and a VQA dataset (DEJIMA-VQA), each containing 3.88M image-text pairs, far exceeding the size of existing Japanese V&L datasets. Human evaluations demonstrate that DEJIMA achieves substantially higher Japaneseness and linguistic naturalness than datasets constructed via translation or manual annotation, while maintaining factual correctness at a level comparable to human-annotated corpora. Quantitative analyses of image feature distributions further confirm that DEJIMA broadly covers diverse visual domains characteristic of Japan, complementing its linguistic and cultural representativeness. Models trained on DEJIMA exhibit consistent improvements across multiple Japanese multimodal benchmarks, confirming that culturally grounded, large-scale resources play a key role in enhancing model performance. All data sources and modules in our pipeline are licensed for commercial use, and we publicly release the resulting dataset and metadata to encourage further research and industrial applications in Japanese V&L modeling.

Blind people have limited opportunities to explore an environment based on their interests.While existing navigation systems could provide them with surrounding information while navigating, they have limited scalability as they require preparing prebuilt maps.Thus, to develop a map-less robot that assists blind people in exploring, we first conducted a study with ten blind participants at a shopping mall and science museum to investigate the requirements of the system, which revealed the need for three levels of detail to describe the surroundings based on users' preferences.Then, we developed WanderGuide, with functionalities that allow users to adjust the level of detail in descriptions and verbally interact with the system to ask questions about the environment or to go to points of interest.The study with five blind participants revealed that WanderGuide could provide blind people with the enjoyable experience of wandering around without a specific destination in their minds.

Abstract In real-world object recognition, there are numerous object classes to be recognized. Traditional image recognition methods based on supervised learning can only recognize object classes present in the training data, and have limited applicability in the real world. In contrast, humans can recognize novel objects by questioning and acquiring knowledge about them. Inspired by this, we propose a framework for acquiring external knowledge by generating questions that enable the model to instantly recognize novel objects. Our framework comprises three components: the object classifier (OC), which performs knowledge-based object recognition, the question generator (QG), which generates knowledge-aware questions to acquire novel knowledge, and the policy decision (PD) Model, which determines the “policy” of questions to be asked. The PD model utilizes two strategies, namely “confirmation” and “exploration”—the former confirms candidate knowledge while the latter explores completely new knowledge. Our experiments demonstrate that the proposed pipeline effectively acquires knowledge about novel objects compared to several baselines, and realizes novel object recognition utilizing the obtained knowledge. We also performed a real-world evaluation in which humans responded to the generated questions, and the model used the acquired knowledge to retrain the OC, which is a fundamental step toward a real-world human-in-the-loop learning-by-asking framework. We plan to release the dataset immediately upon acceptance of our work.

Visual Question Generation (VQG) is a task to generate questions from images. When humans ask questions about an image, their goal is often to acquire some new knowledge. However, existing studies on VQG have mainly addressed question generation from answers or question categories, overlooking the objectives of knowledge acquisition. To introduce a knowledge acquisition perspective into VQG, we constructed a novel knowledge-aware VQG dataset called K-VQG. This is the first large, humanly annotated dataset in which questions regarding images are tied to structured knowledge. We also developed a new VQG model that can encode and use knowledge as the target for a question. The experiment results show that our model outperforms existing models on the K-VQG dataset. Our dataset is publicly available at https://uehara-mech.github.io/kvqg.