Automatic Recognition of Facial Actions in Spontaneous Expressions

By M. Bartlett, Gwen Littlewort, Mark G. Frank, Claudia Lainscsek, Ian R. Fasel, Javier R. Movellan. J. Multim., 2006

543 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/cbe7deabc11b4b95032f97322bbef5239d5a84ca

How researchers see this paper

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

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

In Human-Computer Interaction

Citations in the corpus

CASME database: A dataset of spontaneous micro-expressions collected from neutralized faces (2013, background): “AUs give detailed movements of facial expressions and help to give more accurate emotion labels [14][15].”
A Spontaneous Micro-expression Database: Inducement, collection and baseline (2013, background): “CK [12] 210 adults 480 videos 6 classes Posed MMI [13] 79 adults + 1250 videos + 6 classes Posed + 11 childrens 600 images + AUs Spontaneous JAFFE [14] 10 females 213 images 6 classes Posed + neutral RU-FACS [15] 100 adults 100 videos AUs Spontaneous Multi-PIE [16] 100 adults 4200 images 6 classes P”
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis (2016, background): “In the last 10 years, research on facial expression analysis has shifted its focus from posed behavior to non-posed (i.e., spontaneous) behavior [34] [2] [14] [17] [23].”
Painful data: The UNBC-McMaster shoulder pain expression archive database (2011, background): “From initial focus on posed images recorded from a frontal view, current efforts extend to posed data recorded from multiple views [4], [5], 3D imaging [6], and, increasingly, non-posed facial behavior in real-world settings in which non-frontal pose and head motion are common [7], [8].”
MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception (2017, methodology): “While CERT is robust to reasonable degree of head rotation, 16 turns were discarded since CERT was not able to track the face.”
SAMM: A Spontaneous Micro-Facial Movement Dataset (2018, background): “For larger facial expressions this can be a much easier task [43], [44] as the movements across people are more clearly deﬁned.”
Facial micro-expressions recognition using high speed camera and 3D-gradient descriptor (2009, methodology): “Unlike Bartlett [8] who applied bank of Gabor filters to all the face area at once, we divide the face to 12 regions of interest.”
Collecting Large, Richly Annotated Facial-Expression Databases from Movies (2012, background): “The MMI database is a searchable temporal database with 75 subjects.(6) All of these are posed, lab-controlled environment databases.”
Toward Practical Smile Detection (2009, methodology): “Earlier research on detecting facial actions using SVMs [39] has shown empirically that the distance to the margin of the SVM output is correlated with”
Image based Static Facial Expression Recognition with Multiple Deep Network Learning (2015, background): “Categories and Subject Descriptors I.5.4 [Pattern Recognition]: Applications—computer vision, signal processing ; I.4.m [Image Processing and Computer Vision]: Miscellaneous Keywords Facial Expression Recognition; Convolutional Neural Network; Multiple Network Learning; EmotiW 2015 Challenge”
Coarse scales are sufﬁcient for efﬁcient categorization of emotional facial expressions: Evidence from neural computation (unknown): “It should also be noted that, with this larger training set, our neural network (which uses a simpler method which eliminates spatial information) performed categorization as efﬁciently as the best references in the ﬁeld, which use Gabor ﬁlters the spatial domain [2,4,15,16].”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, background): “Even though attempts in estimating FE intensity have existed before [234], the first seminal work was published in 2006 [235].”
Coarse scales are sufficient for efficient categorization of emotional facial expressions: Evidence from neural computation (2010, methodology): “The purpose of the present article is to determine whether LSF components are sufficient for efficient categorization of an EFE.”
Supervised Descent Method and Its Applications to Face Alignment (2013, methodology): “We evaluated SDM’s tracking performance on two datasets, RU-FACS [3] and Youtube Celebrities [20].”
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement (2023, methodology): “The convolution strides are set as [1, 2, 2, 1].”
DISFA: A Spontaneous Facial Action Intensity Database (2013, unknown): “Exceptions include [35], [37], [38], [39].”
The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression (2010, methodology): “This is a common problem across the many publicly available datasets currently available such as the MMI [19] and RUFACS [4] databases (see Zeng et al. [27] for a thorough survey of currently available databases).”