@inbook{1572f7826828488bbdc9642cdeea863c,
title = "Multimodal Integration for Meeting Group Action Segmentation and Recognition",
abstract = "We address the problem of segmentation and recognition of sequences of multimodal human interactions in meetings. These interactions can be seen as a rough structure of a meeting, and can be used either as input for a meeting browser or as a first step towards a higher semantic analysis of the meeting. A common lexicon of multimodal group meeting actions, a shared meeting data set, and a common evaluation procedure enable us to compare the different approaches. We compare three different multimodal feature sets and our modelling infrastructures: a higher semantic feature approach, multi-layer HMMs, a multi-stream DBN, as well as a multi-stream mixed-state DBN for disturbed data.",
author = "Marc Al-Hames and Alfred Dielmann and Daniel Gatica-Perez and Stephan Reiter and Steve Renals and Gerhard Rigoll and Dong Zhang",
year = "2006",
doi = "10.1007/11677482_5",
language = "English",
isbn = "978-3-540-32549-9",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "52--63",
editor = "Steve Renals and Samy Bengio",
booktitle = "Machine Learning for Multimodal Interaction: Second International Workshop, MLMI 2005, Edinburgh, UK, July 11-13, 2005, Revised Selected Papers",
address = "United Kingdom",
note = "Second International Workshop (MLMI 2005) ; Conference date: 11-07-2005 Through 13-07-2005",
}