15 citations · 16 across the 4 of their papers we have counts for
4 papers
Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environments
Takanori Ugai, Kensho Hara, Shusaku Egami +1
We used a 3D simulator to create artificial video data with standardized annotations, aiming to aid in the development of Embodied AI. Our question answering (QA) dataset measures…
VHAKG: A Multi-modal Knowledge Graph Based on Synchronized Multi-view Videos of Daily Activities
Shusaku Egami, Takahiro Ugai, Swe Nwe Nwe Htun +1
Multi-modal knowledge graphs (MMKGs), which ground various non-symbolic data (e.g., images and videos) into symbols, have attracted attention as resources enabling knowledge proces…
Synthetic Multimodal Dataset for Empowering Safety and Well-being in Home Environments
Takanori Ugai, Shusaku Egami, Swe Nwe Nwe Htun +3
This paper presents a synthetic multimodal dataset of daily activities that fuses video data from a 3D virtual space simulator with knowledge graphs depicting the spatiotemporal co…
Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space
Shusaku Egami, Takanori Ugai, Mikiko Oono +2
Artificial intelligence (AI) is expected to be embodied in software agents, robots, and cyber-physical systems that can understand the various contextual information of daily life…