Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain

Ute Schmid, Michael Siebers, Dominik Seuß, Miriam Kunz, Stefan Lautenbacher
; Proceedings of the Eleventh International Conference on Grammatical Inference, PMLR 21:183-188, 2012.

Abstract

We present an application of grammar inference in the domain of facial expression analysis. Typically, only sets of AUs which occur in a given time frame are used for expression analysis, the sequence in which these AUs occur is ignored. We wanted to explore whether the strucural patterns of AU appearances contain diagnostically relevant information. We applied alignment-based learning (ABL) to data of facial expressions of pain collected in a psychological study. To evaluate the quality of the induced grammars we applied cross-validation to estimate the generalization error. We can show that the learned grammars have reasonably high coverages for unseen pain sequences. However, the number of rules of the learned grammars cannot be reduced substantially without loss of generalization.

Cite this Paper


BibTeX
@InProceedings{pmlr-v21-schmid12a, title = {Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain}, author = {Ute Schmid and Michael Siebers and Dominik Seuß and Miriam Kunz and Stefan Lautenbacher}, booktitle = {Proceedings of the Eleventh International Conference on Grammatical Inference}, pages = {183--188}, year = {2012}, editor = {Jeffrey Heinz and Colin Higuera and Tim Oates}, volume = {21}, series = {Proceedings of Machine Learning Research}, address = {University of Maryland, College Park, MD, USA}, month = {05--08 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v21/schmid12a/schmid12a.pdf}, url = {http://proceedings.mlr.press/v21/schmid12a.html}, abstract = {We present an application of grammar inference in the domain of facial expression analysis. Typically, only sets of AUs which occur in a given time frame are used for expression analysis, the sequence in which these AUs occur is ignored. We wanted to explore whether the strucural patterns of AU appearances contain diagnostically relevant information. We applied alignment-based learning (ABL) to data of facial expressions of pain collected in a psychological study. To evaluate the quality of the induced grammars we applied cross-validation to estimate the generalization error. We can show that the learned grammars have reasonably high coverages for unseen pain sequences. However, the number of rules of the learned grammars cannot be reduced substantially without loss of generalization.} }
Endnote
%0 Conference Paper %T Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain %A Ute Schmid %A Michael Siebers %A Dominik Seuß %A Miriam Kunz %A Stefan Lautenbacher %B Proceedings of the Eleventh International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2012 %E Jeffrey Heinz %E Colin Higuera %E Tim Oates %F pmlr-v21-schmid12a %I PMLR %J Proceedings of Machine Learning Research %P 183--188 %U http://proceedings.mlr.press %V 21 %W PMLR %X We present an application of grammar inference in the domain of facial expression analysis. Typically, only sets of AUs which occur in a given time frame are used for expression analysis, the sequence in which these AUs occur is ignored. We wanted to explore whether the strucural patterns of AU appearances contain diagnostically relevant information. We applied alignment-based learning (ABL) to data of facial expressions of pain collected in a psychological study. To evaluate the quality of the induced grammars we applied cross-validation to estimate the generalization error. We can show that the learned grammars have reasonably high coverages for unseen pain sequences. However, the number of rules of the learned grammars cannot be reduced substantially without loss of generalization.
RIS
TY - CPAPER TI - Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain AU - Ute Schmid AU - Michael Siebers AU - Dominik Seuß AU - Miriam Kunz AU - Stefan Lautenbacher BT - Proceedings of the Eleventh International Conference on Grammatical Inference PY - 2012/08/16 DA - 2012/08/16 ED - Jeffrey Heinz ED - Colin Higuera ED - Tim Oates ID - pmlr-v21-schmid12a PB - PMLR SP - 183 DP - PMLR EP - 188 L1 - http://proceedings.mlr.press/v21/schmid12a/schmid12a.pdf UR - http://proceedings.mlr.press/v21/schmid12a.html AB - We present an application of grammar inference in the domain of facial expression analysis. Typically, only sets of AUs which occur in a given time frame are used for expression analysis, the sequence in which these AUs occur is ignored. We wanted to explore whether the strucural patterns of AU appearances contain diagnostically relevant information. We applied alignment-based learning (ABL) to data of facial expressions of pain collected in a psychological study. To evaluate the quality of the induced grammars we applied cross-validation to estimate the generalization error. We can show that the learned grammars have reasonably high coverages for unseen pain sequences. However, the number of rules of the learned grammars cannot be reduced substantially without loss of generalization. ER -
APA
Schmid, U., Siebers, M., Seuß, D., Kunz, M. & Lautenbacher, S.. (2012). Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain. Proceedings of the Eleventh International Conference on Grammatical Inference, in PMLR 21:183-188

Related Material