@inbook{88caad320f224cc9a8c73c7f84568218,
title = "An Enhanced Intelligent Agent with Image Description Generation",
abstract = "In this paper, we present an Embodied Conversational Agent (ECA) enriched with automatic image understanding, using vision data derived from state-of-the-art machine learning techniques for the advancement of autonomous interaction with the elderly or infirm. The agent is developed to conduct health and emotion well-being monitoring for the elderly. It is not only able to conduct question-answering via speech-based interaction, but also able to provide analysis of the user{\textquoteright}s surroundings, company, emotional states, hazards and fall actions via visual data using deep learning techniques. The agent is accessible from a web browser and can be communicated with via voice means, with a webcam required for the visual analysis functionality. The system has been evaluated with diverse real-life images to prove its efficiency.",
keywords = "Intelligent conversational agent, Image description generation, Human agent interaction",
author = "Ben Fielding and Philip Kinghorn and Kamlesh Mistry and Li Zhang",
year = "2016",
month = nov,
day = "23",
doi = "10.1007/978-3-319-47665-0_10",
language = "English",
isbn = "978-3-319-47664-3",
volume = "10011",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "110--119",
booktitle = "Intelligent Virtual Agents",
address = "Germany",
}