%Aigaion2 BibTeX export from Idiap Publications
%Thursday 04 December 2025 07:37:38 PM

@INPROCEEDINGS{zhang-rr-05-31b,
                      author = {Al-Hames, Marc and Dielmann, Alfred and Gatica-Perez, Daniel and Reiter, Stephan and Renals, Steve and Zhang, Dong},
                    projects = {Idiap},
                       title = {{Multimodal Integration for Meeting Group Action Segmentation and Recognition}},
                   booktitle = {MLMI},
                        year = {2005},
                        note = {IDIAP-RR 05-31},
                    crossref = {zhang-rr-05-31},
                    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 four 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.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2005/mlmi-05-joint.pdf},
                  postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr-05-31.ps.gz},
ipdmembership={vision},
}



crossreferenced publications: 
@TECHREPORT{zhang-rr-05-31,
                      author = {Al-Hames, Marc and Dielmann, Alfred and Gatica-Perez, Daniel and Reiter, Stephan and Renals, Steve and Zhang, Dong},
                    projects = {Idiap},
                       title = {{Multimodal Integration for Meeting Group Action Segmentation and Recognition}},
                        type = {Idiap-RR},
                      number = {Idiap-RR-31-2005},
                        year = {2005},
                 institution = {IDIAP},
                     address = {Martigny, Switzerland},
                        note = {Published in ``MLMI'', July, 2005},
                    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 four 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.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2005/rr-05-31.pdf},
                  postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr-05-31.ps.gz},
ipdinar={2005},
ipdmembership={vision},
language={English},
}