Markov Random Field Structures for Facial Action Unit Intensity Estimation
Abstract
We present a novel Markov Random Field (MRF) structure-based approach to the problem of facial action unit (AU) intensity estimation. AUs generally appear in common combinations, and exhibit strong relationships between the intensities of a number of AUs. The aim of this work is to harness these links in order to improve the estimation of the intensity values over that possible from regression of individual AUs. Our method exploits Support Vector Regression outputs to model appearance likelihoods of each individual AU, and integrates these with intensity combination priors in MRF structures to improve the overall intensity estimates. We demonstrate the benefits of our approach on the upper face AUs annotated in the DISFA database, with significant improvements seen in both correlation and error rates for the majority of AUs, and on average.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Some works use probabilistic models of AUs combination likelihoods and intensity priors for improving performance.
“In order to overcome such limitations some works use probabilistic models of AUs combination likelihoods and intensity priors for improving performance [239], [240].”
From Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications (2016) · cites this paper as [239]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Prkachin, K. M., & Solomon, P. E. (2008) · Pain · doi:10.1016/j.pain.2008.04.010 · Cited by 472 · see citing works
Continuous Pain Intensity Estimation from Facial Expressions
Kaltwang, S., Rudovic, O., & Pantic, M. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33191-6_36 · Cited by 245 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Corneanu, C. A., Simon, M. O., Cohn, J. F., & Guerrero, S. E. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2515606 · Cited by 527 · see citing works
- Authors
- Sandbach, G., Zafeiriou, S., & Pantic, M.
- Affiliations
- Imperial College London (GB)
- ORCID
- Zafeiriou, Stefanos
- Venue
- 2013 IEEE International Conference on Computer Vision Workshops
- Publisher
- IEEE
- Published
- 2013-12
- Pages
- 738-745
- ISSN
- 2473-9936 (ISSN-L)
- OpenAlex
- W1964277727
- Cited by
- 60
- References
- 2
- Citations by year
- 2025: 1 · 2024: 1 · 2022: 4 · 2021: 3 · 2020: 5 · 2019: 9 · 2018: 8 · 2017: 9 · 2016: 9 · 2015: 8 · 2014: 3
- FWCI
- 4.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Computer Vision Workshops (publishedVersion)
- Funders
- Engineering and Physical Sciences Research Council (EP/J017787/1, EP/H016988/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Keywords
- facial action units, Markov random fields, support vector regression, facial expression analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
