Markov Random Field Structures for Facial Action Unit Intensity Estimation

被引：40
|
作者：
Sandbach, Georgia [1 ]
Zafeiriou, Stefanos [1 ]
Pantic, Maja [1 ,2 ]
机构：
[1] Univ London Imperial Coll Sci Technol & Med, Dept Comp, London, England
[2] Univ Twente, EEMCS, NL-7522 NB Enschede, Netherlands
来源：
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2013年
基金：
英国工程与自然科学研究理事会;
关键词：
POSE ESTIMATION; PAIN;
D O I：
10.1109/ICCVW.2013.101
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：738 / 745
页数：8
相关论文
共 50 条
  • [31] Multi-Output Random Forests for Facial Action Unit Detection
    Dapogny, Arnaud
    Bailly, Kevin
    Dubuisson, Severine
    [J]. 2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017), 2017, : 135 - 140
  • [32] RECURSIVE ESTIMATION OF INTENSITY FUNCTION OF A POISSON RANDOM FIELD
    ROZANSKI, R
    [J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1992, 33 (02) : 165 - 174
  • [33] Parameter estimation in Markov Random Field based on Evolutionary Programming
    School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
    [J]. Moshi Shibie yu Rengong Zhineng, 2006, 2 (143-148):
  • [34] Theory of Distribution Estimation of Hyperparameters in Markov Random Field Models
    Sakamoto, Hirotaka
    Nakanishi-Ohno, Yoshinori
    Okada, Masato
    [J]. JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 2016, 85 (06)
  • [35] Crowd Density Estimation via Markov Random Field (MRF)
    Guo, Jinnian
    Wu, Xinyu
    Cao, Tian
    Yu, Shiqi
    Xu, Yangsheng
    [J]. 2010 8TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2010, : 258 - 263
  • [36] Parameter estimation in Markov random field based on evolutionarty programming
    Shao, C
    Huang, HK
    Yu, R
    [J]. PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 3814 - 3819
  • [37] Pain Classification and Intensity Estimation Through the Analysis of Facial Action Units
    Paoli, Federica
    D'Eusanio, Andrea
    Cozzi, Federico
    Patania, Sabrina
    Boccignone, Giuseppe
    [J]. IMAGE ANALYSIS AND PROCESSING - ICIAP 2023 WORKSHOPS, PT I, 2024, 14365 : 229 - 241
  • [38] Intensity Estimation of Spontaneous Facial Action Units Based on Their Sparsity Properties
    Mohammadi, Mohammad Reza
    Fatemizadeh, Emad
    Mahoor, Mohammad H.
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (03) : 817 - 826
  • [39] SPATIOTEMPORAL FEATURES AND LOCAL RELATIONSHIP LEARNING FOR FACIAL ACTION UNIT INTENSITY REGRESSION
    Wei, Chao
    Lu, Ke
    Gan, Wei
    Xue, Jian
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 1109 - 1113
  • [40] Simple and Effective Approaches for Uncertainty Prediction in Facial Action Unit Intensity Regression
    Wortwein, Torsten
    Morency, Louis-Philippe
    [J]. 2020 15TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2020), 2020, : 452 - 456
12345