In this paper, we review the major approaches to multimodal human-computer interaction, giving an overview of the field from a computer vision perspective. In particular, we focus on body, gesture, gaze, and affective interaction (facial expression recognition and emotion in audio). We discuss user and task modeling, and multimodal fusion, highlighting challenges, open issues, and emerging applications for multimodal human-computer interaction (MMHCI) research.
%0 Journal Article
%1 JaimesSebe07cviu
%A Jaimes, Alejandro
%A Sebe, Nicu
%D 2007
%J Computer Vision and Image Understanding
%K v1205 paper ai multimodal user interface image recognition video analysis interaction emotion zzz.th.c4
%N 1-2
%P 116-134
%R 10.1016/j.cviu.2006.10.019
%T Multimodal Human-Computer Interaction: A Survey
%V 108
%X In this paper, we review the major approaches to multimodal human-computer interaction, giving an overview of the field from a computer vision perspective. In particular, we focus on body, gesture, gaze, and affective interaction (facial expression recognition and emotion in audio). We discuss user and task modeling, and multimodal fusion, highlighting challenges, open issues, and emerging applications for multimodal human-computer interaction (MMHCI) research.
@article{JaimesSebe07cviu,
abstract = {In this paper, we review the major approaches to multimodal human-computer interaction, giving an overview of the field from a computer vision perspective. In particular, we focus on body, gesture, gaze, and affective interaction (facial expression recognition and emotion in audio). We discuss user and task modeling, and multimodal fusion, highlighting challenges, open issues, and emerging applications for multimodal human-computer interaction ({MMHCI}) research.},
added-at = {2012-05-30T10:48:31.000+0200},
author = {Jaimes, Alejandro and Sebe, Nicu},
biburl = {https://www.bibsonomy.org/bibtex/28c164294f04f3bf670fd48b0a28945c2/flint63},
doi = {10.1016/j.cviu.2006.10.019},
file = {Preprint ICCV 2005:2007/JaimesSebe07cviu.pdf:PDF},
groups = {public},
interhash = {778b8b2ef24743815fa4607105ec2deb},
intrahash = {8c164294f04f3bf670fd48b0a28945c2},
issn = {1077-3142},
journal = {Computer Vision and Image Understanding},
keywords = {v1205 paper ai multimodal user interface image recognition video analysis interaction emotion zzz.th.c4},
month = {#oct#},
number = {1-2},
pages = {116-134},
timestamp = {2018-04-16T11:54:22.000+0200},
title = {Multimodal Human-Computer Interaction: A Survey},
username = {flint63},
volume = 108,
year = 2007
}