Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 192

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

Selective Transfer Machine for Personalized Facial Expression Analysis

Open access
Chu, Wen-Sheng, De la Torre, Fernando, Cohn, Jeffrey F.·2017·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Automatic facial action unit (AU) and expression detection from videos is a long-standing problem. The problem is challenging in part because classifiers must generalize to previously unknown subjects that differ markedly in behavior and facial morphology (e.g., heavy versus delicate brows, smooth versus deeply etched wrinkles) from those on which the classifiers are trained. While some progress has been achieved through improvements in choices of features and classifiers, the challenge occasioned by individual differences among people remains. Person-specific classifiers would be a possible solution but for a paucity of training data. Sufficient training data for person-specific classifiers typically is unavailable. This paper addresses the problem of how to personalize a generic classifier without additional labels from the test subject. We propose a transductive learning method, which we refer to as a Selective Transfer Machine (STM), to personalize a generic classifier by attenuating person-specific mismatches. STM achieves this effect by simultaneously learning a classifier and re-weighting the training samples that are most relevant to the test subject. We compared STM to both generic classifiers and cross-domain learning methods on four benchmarks: CK+ [44], GEMEP-FERA [67], RUFACS [4] and GFT [57]. STM outperformed generic classifiers in all.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2016.2547397

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 12 references

Research works printed but not linked: 73

  1. 10.1093/acprof:oso/9780195387643.003.0007 · DOI
  2. 10.1287/opre.24.4.643 · doi:10.1287/opre.24.4.643
  3. 10.1109/CVPR.2013.439 · DOI
  4. 10.1145/1291233.1291276 · DOI · Paper page
  5. 10.1109/CVPR.2010.5539978 · DOI
  6. 10.1109/CVPR.2013.75 · DOI · Paper page
  7. khosla, 0, Undoing the damage of dataset bias, Proc 10th Eur Conf Comput Vis, 158-171
  8. 10.1007/978-3-642-33765-9_48 · DOI
  9. 10.1145/1101149.1101300 · DOI · Paper page
  10. 10.1007/978-3-319-14364-4_26 · doi:10.1007/978-3-319-14364-4_26
  11. 10.1145/2663204.2663247 · DOI
  12. guo, 0, Dynamic facial expression recognition using longitudinal facial expression atlases, Proc 10th Eur Conf Comput Vis, 631
  13. gretton, 2009, Covariate shift by kernel mean matching, Dataset Shift Mach Learn, 131
  14. 10.1007/s00186-007-0161-1 · DOI · Paper page
  15. 10.1109/AFGR.2000.840611 · DOI · Paper page
  16. joachims, 0, Transductive inference for text classification using support vector machines, Proc Int Conf Mach Learn, 200
  17. 10.1109/FG.2011.5771416 · DOI · Paper page
  18. 10.1109/FG.2015.7163142 · DOI · Paper page
  19. sikka, 0, Exploring bag of words architectures in the facial expression domain, Proc 12th Int Conf Comput Vision, 250-259
  20. 10.1109/CVPR.2010.5539998 · DOI
  21. sugiyama, 2007, Covariate shift adaptation by importance weighted cross validation, J Mach Learning Res, 8, 985
  22. girard, 2014, Spontaneous facial expression in unscripted social interactions can be measured automatically, Behavior Research Methods, 47, 1136-1147
  23. sugiyama, 0, Direct importance estimation with model selection and its application to covariate shift adaptation, Proc Adv Neural Inf Process Syst, 1433
  24. 10.1109/CVPRW.2011.5981817 · DOI
  25. 10.1109/TPAMI.2007.1094 · DOI · Paper page
  26. 10.1109/TSMCB.2011.2163710 · DOI · Paper page
  27. 10.1023/B:MACH.0000008082.80494.e0 · DOI · Paper page
  28. 10.1109/ICCV.2011.6126504 · DOI · Paper page
  29. 10.1007/BF02764940 · doi:10.1007/bf02764940
  30. 10.1007/978-0-85729-997-0_19 · DOI
  31. 10.1109/TPAMI.2011.114 · DOI · Paper page
  32. 10.1109/ICCV.2013.298 · DOI
  33. dud?k, 0, Correcting sample selection bias in maximum entropy density estimation, Proc Adv Neural Inf Process Syst, 323
  34. 10.1109/TNNLS.2011.2178556 · DOI · Paper page
  35. 10.1016/0098-1354(90)80020-C · DOI · Paper page
  36. 10.1109/ICCV.2013.368 · DOI · Paper page
  37. 10.1109/FG.2013.6553779 · DOI
  38. shang, 0, Nonparametric discriminant HMM and application to facial expression recognition, Proc IEEE Conf Comput Vis Pattern Recog, 2090
  39. 10.1109/TSMCB.2012.2193567 · DOI
  40. 10.1177/0956797611435134 · DOI · Paper page
  41. 10.1109/TPAMI.2014.2366127 · DOI · Paper page
  42. 10.1145/2647868.2654916 · DOI
  43. 10.1109/TPAMI.2014.2356192 · DOI
  44. rudovic, 0, Kernel conditional ordinal random fields for temporal segmentation of facial action units, Proc European Conf Comp Vis Workshop, 260
  45. 10.1016/j.imavis.2005.08.006 · DOI · Paper page
  46. 10.1162/neco.2007.19.5.1155 · DOI · Paper page
  47. 10.1109/CVPR.2011.5995702 · DOI · Paper page
  48. 10.1145/2382577.2382582 · DOI
  49. chen, 0, Switching Gaussian process dynamic models for simultaneous composite motion tracking and recognition, Proc IEEE Conf Comput Vis Pattern Recog, 2655
  50. 10.1016/j.patrec.2013.02.002 · DOI
  51. 10.1109/FG.2011.5771373 · DOI
  52. 10.1109/TPAMI.2007.1110 · DOI · Paper page
  53. 10.1109/TSMCB.2012.2194485 · DOI
  54. 10.1109/CVPR.2006.301 · DOI · Paper page
  55. collobert, 2006, Large scale transductive SVMs, J Mach Learning Res, 7, 1687
  56. zhong, 0, Learning active facial patches for expression analysis, Proc IEEE Conf Comput Vis Pattern Recog, 1499
  57. 10.1109/CVPR.2015.7298833 · DOI · Paper page
  58. daumé iii, 0, Frustratingly easy domain adaptation, Proc Conf Assoc Computational Linguistics, 256
  59. 10.1109/ICCV.2015.413 · DOI
  60. 10.4304/jmm.1.6.22-35 · DOI · Paper page
  61. 10.1109/ICCV.2013.100 · DOI · Paper page
  62. 10.1109/CVPR.2010.5539966 · DOI
  63. 10.1109/IJCNN.2010.5596316 · DOI
  64. zhu, 2011, Dynamic cascades with bidirectional bootstrapping for action unit detection in spontaneous facial behavior, IEEE Trans Affective Comput, 2, 79, 10.1109/T-AFFC.2011.10 · DOI
  65. 10.1145/1961189.1961199 · DOI · Paper page
  66. chang, 0, Learning partially-observed hidden conditional random fields for facial expression recognition, Proc IEEE Conf Comput Vis Pattern Recog, 533
  67. martinez, 2012, A model of the perception of facial expressions of emotion by humans: Research overview and perspectives, J Mach Learning Res, 13, 1589
  68. 10.5772/4841 · DOI · Paper page
  69. 10.1007/978-3-642-02172-5_24 · DOI
  70. 10.1023/B:VISI.0000029666.37597.d3 · DOI · Paper page
  71. liu, 0, AU-aware deep networks for facial expression recognition, Proc IEEE Conf Autom Face Gesture Recog, 1
  72. 10.1109/FG.2011.5771414 · DOI · Paper page
  73. lucas, 1981, An iterative image registration technique with an application to stereo vision, Proc Int Joint Conf Artif Intell, 674

Cited by

See all 192

Metadata

Authors
Chu, W.-S., De la Torre, F., & Cohn, J. F.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2017-03-01
Volume
39
Issue
3
Pages
529-545
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W2326887180
Cited by
192
References
12
FWCI
33.14
Type
journal article
Language
en
Open access
green
Funders
  • National Institutes of Health (R01MH096951)
  • National Science Foundation (RI-1116583)
  • Army Research Laboratory Collaborative Technology Alliance Program (W911NF-10-2-0016)
  • NIH
  • NSF

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Selective Transfer Machine for Personalized Facial Expression Analysis. https://app.cochat.ai/papers/10.1109/tpami.2016.2547397
The paper
Chu, W.-S., De la Torre, F., & Cohn, J. F. (2017). Selective Transfer Machine for Personalized Facial Expression Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2016.2547397

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.