The Detection of Concept Frames Using Clustering Multi-instance Learning
- Resource Type
- Conference
- Authors
- Tax, D.M.J.; Hendriks, E.; Valstar, M.F.; Pantic, M.
- Source
- 2010 20th International Conference on Pattern Recognition Pattern Recognition (ICPR), 2010 20th International Conference on. :2917-2920 Aug, 2010
- Subject
- Computing and Processing
Hidden Markov models
Training
Gold
Logistics
Time series analysis
Data models
Pattern recognition
classification
multi-instance learning
time series classification
- Language
- ISSN
- 1051-4651
The classification of sequences requires the combination of information from different time points. In this paper the detection of facial expressions is considered. Experiments on the detection of certain facial muscle activations in videos show that it is not always required to model the sequences fully, but that the presence of specific frames (the concept frame) can be sufficient for a reliable detection of certain facial expression classes. For the detection of these concept frames a standard classifier is often sufficient, although a more advanced clustering approach performs better in some cases.