Virtual assistant: enhancing content acquisition by eliciting information from humans

In this paper, we propose the “Virtual Assistant,” a novel framework for supporting knowledge capturing in videos. The Virtual Assistant is an artificial agent that simulates a human assistant shown in TV programs and prompts users to provide feedback by asking questions. This framework ensures that sufficient information is provided in the captured content while users interact in a natural and enjoyable way with the agent. We developed a prototype agent based on a chatbot-like approach and applied it to a daily cooking scene. Experimental results demonstrate the potential of the Virtual Assistant framework, as it allows a person to provide feedback easily with few interruptions and elicits a variety of useful information.

Yuichi NakamuraEmail: URL: http://www.ccm.media.kyoto-u.ac.jp/index.php

---

Motoyuki Ozeki   received his B.E, M.E. and Ph.D. degrees in engineering from University of Tsukuba, in 2000 and 2005, respectively. He worked as an assistant professor at Kyoto University since 2005. He is currently an assistant professor at Kyoto Institute of Technology. His research interests are in the areas of human-agent interaction and cognitive science. Shunichi Maeda   received his B.E and M.E. degrees in electronical engineering from Kyoto University, in 2008. He is currently working in Patent Office (KAJI-SUHARA & ASSOCIATES). Kanako Obata   received her B.E. degree in economics from Osaka Prefecture University in2004. She is currently an educational assistant at Kyoto University as since 2004. Her research interests are human-communication and cooking. Yuichi Nakamura   received his BE degree in 1985, his ME and PhD degrees in electronical engineering from Kyoto University in 1987 and 1992, respectively. He worked as assistant professor at University of Tsukuba since 1993 and as associate professor since 1999. He is currently a professor at Kyoto University. His research interests and activities include human-computer interactions, video analysis, and video utilization for knowledge sources.