@INPROCEEDINGS{SheermanChase2009b,
  author = {Sheerman-Chase, Tim and Ong, Eng-Jon and Bowden, Richard},
  title = {Online Learning of Robust Facial Feature Trackers},
  booktitle = {3rd IEEE On-line Learning for Computer Vision Workshop},
  year = {2009},
  address = {Kyoto},
  month = {Oct},
  abstract = {This paper presents a head pose and facial feature estimation technique
	that works over a wide range of pose variations without a priori
	knowledge of the appearance of the face. Using simple LK trackers,
	head pose is estimated by Levenberg-Marquardt (LM) pose estimation
	using the feature tracking as constraints. Factored sampling and
	RANSAC are employed to both provide a robust pose estimate and identify
	tracker drift by constraining outliers in the estimation process.
	The system provides both a head pose estimate and the position of
	facial features and is capable of tracking over a wide range of head
	poses.},
  keywords = {head pose online ransac lk tracking},
  owner = {ts00051},
  timestamp = {2009.10.26}
}

@INPROCEEDINGS{SheermanChase2009,
  author = {Sheerman-Chase, Tim and Ong, Eng-Jon and Bowden, Richard},
  title = {Feature Selection of Facial Displays for Detection of Non Verbal
	Communication in Natural Conversation},
  booktitle = {IEEE International Workshop on Human-Computer Interaction},
  year = {2009},
  address = {Kyoto},
  month = {Oct},
  abstract = {Recognition of human communication has previously focused on deliberately
	acted emotions or in structured or artificial social contexts. This
	makes the result hard to apply to realistic social situations. This
	paper describes the recording of spontaneous human communication
	in a specific and common social situation: conversation between two
	people. The clips are then annotated by multiple observers to reduce
	individual variations in interpretation of social signals. Temporal
	and static features are generated from tracking using heuristic and
	algorithmic methods. Optimal features for classifying examples of
	spontaneous communication signals are then extracted by AdaBoost.
	The performance of the boosted classifier is comparable to human
	performance for some communication signals, even on this challenging
	and realistic data set.},
  keywords = {feature selection boost adaboost nvc affect natural conversation},
  owner = {ts00051},
  timestamp = {2009.10.26},
  url = {http://personal.ee.surrey.ac.uk/Personal/T.Sheerman-chase/}
}