This paper introduces the Multimodal Multi-view Integrated Database (MMID), which holds human activities in presentation situations. MMID contains audio, video, human body motions...
Yuichi Nakamura, Yoshifumi Kimura, Y. Yu, Yuichi O...
Digitizing ancient books, especially those related to the humanities, is practiced in many countries. The number of full-text databases in the humanities is increasing. Studies hav...
We use graphical models and structure learning to explore how people learn policies in sequential decision making tasks. Studies of sequential decision-making in humans frequently...
As robots become a mass consumer product, they will need to learn new skills by interacting with typical human users. Past approaches have adapted reinforcement learning (RL) to a...
: Acquisition of various human body models is useful in many cases. In this paper, we present some of our recent work on body creation tools. Our goal is to enable rapid creation o...
Hyewon Seo, Frederic Cordier, Laurent Philippon, N...