Painful data: The UNBC-McMaster shoulder pain expression archive database

By Patrick Lucey, Jeffrey F. Cohn, K. Prkachin, Patricia E. Solomon, Iain Matthews. Face and Gesture 2011, 2011

635 citations recorded by the source corpus.

A major factor hindering the deployment of a fully functional automatic facial expression detection system is the lack of representative data. A solution to this is to narrow the context of the target application, so enough data is available to build robust models so high performance can be gained. Automatic pain detection from a patient's face represents one such application. To facilitate this work, researchers at McMaster University and University of Northern British Columbia captured video of participant's faces (who were suffering from shoulder pain) while they were performing a series of active and passive range-of-motion tests to their affected and unaffected limbs on two separate occasions. Each frame of this data was AU coded by certified FACS coders, and self-report and observer measures at the sequence level were taken as well. This database is called the UNBC-McMaster Shoulder Pain Expression Archive Database. To promote and facilitate research into pain and augment current datasets, we have publicly made available a portion of this database which includes: 1) 200 video sequences containing spontaneous facial expressions, 2) 48,398 FACS coded frames, 3) associated pain frame-by-frame scores and sequence-level self-report and observer measures, and 4) 66-point AAM landmarks. This paper documents this data distribution in addition to describing baseline results of our AAM/SVM system. This data will be available for distribution in March 2011.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/e7b55370270a219ff47f5d28cb02c898a6b6a9cb

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

In Human-Computer Interaction

Citations in the corpus

Automatic Analysis of Facial Actions: A Survey (2019, neutral): “AM-FED [117] Induced N/A Various head poses D 10 N N Bosphorous [155] On command 105 subjects 3D multi-pose S 25 N Y BP4D [218] Induced 41 subjects 3D multi-pose D 27 N Y CASME [207] Induced (micro) 35 subjects Near frontal D F Y N CASME II [206] Induced (micro) 26 subjects Near frontal D F Y N Cohn”
Facing Imbalanced Data Recommendations for the Use of Performance Metrics (2013, methodology): “The databases were CohnKanade [21], RU-FACS [13], and UNBC-McMaster Pain Archive [22].”
Multilinear Multitask Learning (2013, methodology): “In the second real world experiment we use the Shoulder Pain dataset (Lucey et al., 2011), which contains video clips of the faces of people who suffer from shoulder pain while performing active and passive exercises.”
Deep Affect Prediction in-the-Wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond (2018, methodology): “Examples include the recently collected EmoPain [4] and UNBC-McMaster [35] databases for analysis of pain, the RU-FACS database of subjects participating in a false opinion scenario [5] and the SEMAINE corpus [38] which contains recordings of subjects interacting with a Sensitive Artiﬁcial Listener…”
BP4D-Spontaneous: a high-resolution spontaneous 3D dynamic facial expression database (2014, background): “While AU 12 is a defining feature of expressed enjoyment, it occurs in pain, embarrassment, and other negative emotions as well as in depression [51,58,59].”
AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild (2017, methodology): “The proposed AU detection approach was trained on CK+ [9], DISFA [14], and CFEE [34] databases, and the accuracy of the automated annotated AUs was reported about 80% on the manually annotated set.”
Learning to Transfer: Transferring Latent Task Structures and Its Application to Person-Specific Facial Action Unit Detection (2015, methodology): “Data: We have used the DISFA dataset [14] and the UNBCMcMaster Shoulder Pain Expression dataset [12] to perform our experiments.”
Categorical and dimensional affect analysis in continuous input: Current trends and future directions (2013, methodology): “McMaster database [102] contains patients with shoulder injuries portraying real or spontaneous pain.”
Federated Learning for Smart Healthcare: A Survey (2021, methodology): “The proposed model is evaluated by using the UNBC-McMaster Shoulder Pain dataset [79], showing that the proposed personalized FL with privacy preserving outperforms the conventional FL approach, which shares all the learning updates with the aggregation server, which in turn increases the probabilit”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, methodology): “Our models are trained on DISFA [48], SEMAINE [51], BP4D [80], UNBC-McMaster [44], Bosphorus [59] and FERA 2011 [66] datasets.”
EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild (2016, methodology): “These databases are: the shoulder pain database of [12], the Denver Intensity of Spontaneous Facial Action (DISFA) dataset of [14], and the database of compound facial expressions of emotion (CFEE) of [7].”