@inproceedings{eb6c56ad36574101b08f9db1811ef69d,
title = "Boosting multi-modal camera selection with semantic features",
abstract = "In this work semantic features are used to improve the results of the camera selection. These semantic features are group action, person action and person speaking. For this purpose low level acoustic and visual features are combined with high level semantic ones. After the feature fusion, a segmentation and classification are performed by Hidden Markov Models. The evaluation shows that an absolute improvement of 6.5% can be achieved. The frame error rate is reduced to 38.1% by using acoustic and all semantic features. The best model using only low level features achieves a frame error rate of 44.6%, which is the best one reported on this data set.",
keywords = "Human-machine interaction, Machine learning, Meeting analysis, Multi cameras, Multi-modal low level features",
author = "Benedikt H{\"o}rnler and Dejan Arsi{\'c} and Bj{\"o}n Schuller and Gerhard Rigoll",
year = "2009",
doi = "10.1109/ICME.2009.5202740",
language = "English",
isbn = "9781424442911",
series = "Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009",
pages = "1298--1301",
booktitle = "Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009",
note = "2009 IEEE International Conference on Multimedia and Expo, ICME 2009 ; Conference date: 28-06-2009 Through 03-07-2009",
}