Results 1 -
8 of
8
A model of the perception of facial expressions of emotion by humans: Research overview and perspectives
- JMLR
"... In cognitive science and neuroscience, there have been two leading models describing how humans perceive and classify facial expressions of emotion – the continuous and the categorical model. The continuous model defines each facial expression of emotion as a feature vector in a face space. This mod ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
(Show Context)
In cognitive science and neuroscience, there have been two leading models describing how humans perceive and classify facial expressions of emotion – the continuous and the categorical model. The continuous model defines each facial expression of emotion as a feature vector in a face space. This model explains, for example, how expressions of emotion can be seen at different intensities. In contrast, the categorical model consists of C classifiers, each
Meta-Analysis of the First Facial . . .
, 2002
"... . . . an active topic in computer science for over two decades, in particular Facial Action Coding System (FACS) Action Unit ..."
Abstract
- Add to MetaCart
. . . an active topic in computer science for over two decades, in particular Facial Action Coding System (FACS) Action Unit
Exemplar Hidden Markov Models for Classification of Facial Expressions in
"... Facial expressions are dynamic events comprised of meaningful temporal segments. A common approach to facial expression recognition in video is to first convert variable-length expression sequences into a vector repre-sentation by computing summary statistics of image-level features or of spatio-tem ..."
Abstract
- Add to MetaCart
(Show Context)
Facial expressions are dynamic events comprised of meaningful temporal segments. A common approach to facial expression recognition in video is to first convert variable-length expression sequences into a vector repre-sentation by computing summary statistics of image-level features or of spatio-temporal features. These represen-tations are then passed to a discriminative classifier such as a support vector machines (SVM). However, these ap-proaches don’t fully exploit the temporal dynamics of fa-cial expressions. Hidden Markov Models (HMMs), provide a method for modeling variable-length expression time-series. Although HMMs have been explored in the past for expression classification, they are rarely used since classi-fication performance is often lower than discriminative ap-proaches, which may be attributed to the challenges of esti-mating generative models. This paper explores an approach for combining the mod-eling strength of HMMs with the discriminative power of SVMs via a model-based similarity framework. Each exam-ple is first instantiated into an Exemplar-HMM model. A probabilistic kernel is then used to compute a kernel ma-trix, to be used along with an SVM classifier. This paper proposes that dynamical models such as HMMs are ad-vantageous for the facial expression problem space, when employed in a discriminative, exemplar-based classifica-tion framework. The approach yields state-of-the-art results on both posed (CK+ and OULU-CASIA) and spontaneous (FEEDTUM and AM-FED) expression datasets highlight-ing the performance advantages of the approach. 1.
From Emotions to Action Units with Hidden and Semi-Hidden-Task Learning
"... Limited annotated training data is a challenging prob-lem in Action Unit recognition. In this paper, we investigate how the use of large databases labelled according to the 6 universal facial expressions can increase the generaliza-tion ability of Action Unit classifiers. For this purpose, we propos ..."
Abstract
- Add to MetaCart
Limited annotated training data is a challenging prob-lem in Action Unit recognition. In this paper, we investigate how the use of large databases labelled according to the 6 universal facial expressions can increase the generaliza-tion ability of Action Unit classifiers. For this purpose, we propose a novel learning framework: Hidden-Task Learn-ing. HTL aims to learn a set of Hidden-Tasks (Action Units) for which samples are not available but, in contrast, train-ing data is easier to obtain from a set of related Visible-Tasks (Facial Expressions). To that end, HTL is able to ex-ploit prior knowledge about the relation between Hidden and Visible-Tasks. In our case, we base this prior knowl-edge on empirical psychological studies providing statisti-cal correlations between Action Units and universal facial expressions. Additionally, we extend HTL to Semi-Hidden Task Learning (SHTL) assuming that Action Unit training samples are also provided. Performing exhaustive exper-iments over four different datasets, we show that HTL and SHTL improve the generalization ability of AU classifiers by training them with additional facial expression data. Addi-tionally, we show that SHTL achieves competitive perfor-mance compared with state-of-the-art Transductive Learn-ing approaches which face the problem of limited training data by using unlabelled test samples during training. 1.
FEPS: An Easy-to-Learn Sensory Substitution System to Perceive Facial Expressions
"... During social communication, people use a range of modal-ity, both verbal and non-verbal, to express their emotions and intentions. The inability to perceive facial and behav-ioral expressions is a setback for people who are blind or visually impaired. A vision-to-auditory sensory substitution syste ..."
Abstract
- Add to MetaCart
(Show Context)
During social communication, people use a range of modal-ity, both verbal and non-verbal, to express their emotions and intentions. The inability to perceive facial and behav-ioral expressions is a setback for people who are blind or visually impaired. A vision-to-auditory sensory substitution system (S3s) may help them to perceive facial behavioral ex-pressions in a variety of social communication settings and contexts. This paper describes the development of a vision-to-auditory S3 system called “Facial Expression Perception through Sound (FEPS) ” designed for natural dyadic conver-sation. The design of the FEPS accounts for the extraction and selection of facial features and their sonification, that may lead to bridging gaps in perception of emotions. In ad-dition, a technique has been developed to train the users to understand facial expressions so that they can associate the sound stimulus with the perception of emotions using a pro-cess called “Sensorimotor Augmentation”. A Pilot usability study was performed using both subjective and objective methods to illustrate the utility of the prototype FEPS. 1.
Article accepted for publication at the 11th IEEE International Conference on Automatic Face & Gesture Recognition How much training data for facial action unit detection?
"... Abstract — By systematically varying the number of subjects and the number of frames per subject, we explored the influence of training set size on appearance and shape-based approaches to facial action unit (AU) detection. Digital video and expert coding of spontaneous facial activity from 80 subje ..."
Abstract
- Add to MetaCart
Abstract — By systematically varying the number of subjects and the number of frames per subject, we explored the influence of training set size on appearance and shape-based approaches to facial action unit (AU) detection. Digital video and expert coding of spontaneous facial activity from 80 subjects (over 350,000 frames) were used to train and test support vector ma-chine classifiers. Appearance features were shape-normalized SIFT descriptors and shape features were 66 facial landmarks. Ten-fold cross-validation was used in all evaluations. Number of subjects and number of frames per subject differentially af-fected appearance and shape-based classifiers. For appearance features, which are high-dimensional, increasing the number of training subjects from 8 to 64 incrementally improved performance, regardless of the number of frames taken from each subject (ranging from 450 through 3600). In contrast, for shape features, increases in the number of training subjects and frames were associated with mixed results. In summary, maximal performance was attained using appearance features from large numbers of subjects with as few as 450 frames per subject. These findings suggest that variation in the number of subjects rather than number of frames per subject yields most efficient performance. I.
measured automatically
"... Spontaneous facial expression in unscripted social interactions can be ..."
