Toward Practical Smile Detection

By J. Whitehill, Gwen Littlewort, Ian R. Fasel, M. Bartlett, Javier R. Movellan. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009

335 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/47fc921add1421ff8adb730df7aa9e7f865bfdeb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

DISFA: A Spontaneous Facial Action Intensity Database (2013, background): “Initial work in some of these application domains is emerging [7], [8], [9], [10].”
The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression (2010, background): “min {np,nn} where np, nn are the number of positive and negative examples [8, 25].”
Modeling Stylized Character Expressions via Deep Learning (2016, background): “These features can be geometry based such as facial landmarks [16,17], appearance based such as Local Binary Patterns (LBP) [18], Gabor filters [19], Haar features [20], Histogram of Oriented Gradients [21], or motion based such as optical flow [22] and Volume LBP [23].”
Factorized Variational Autoencoders for Modeling Audience Reactions to Movies (2017, background): “A plethora of work in automatically measuring a person’s behavior using vision-based approaches has centered on recognizing an individual’s facial expression [50].”
Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark (2011, methodology): “On the basis of the descriptor type, facial expression analysis methods can be divided into three categories: geometric based [2, 27, 7], appearance based [8, 26, 25] and a combination of both [14].”
Facial Expression Recognition via a Boosted Deep Belief Network (2014, methodology): “These features can be either hand-designed [32, 33, 34, 25, 1, 27, 28, 26, 22, 9, 4, 10, 13] or learned from training images [6, 29, 15, 16, 36, 2, 35, 30].”
The computer expression recognition toolbox (CERT) (2011, background): “Comparisons of Haar+GentleBoost versus Gabor+SVMs showed that the former approach is faster and yields slightly higher accuracy for the smile detection problem [22].”
Painful data: The UNBC-McMaster shoulder pain expression archive database (2011, background): “min {np,nn} where np, nn are the number of positive and negative examples [28], [8].”