• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

An Action Unit co-occurrence constraint 3DCNN based Action Unit recognition approach

Vol. 14, No. 3, March 31, 2020
10.3837/tiis.2020.03.001, Download Paper (Free):

Abstract

The facial expression is diverse and various among persons due to the impact of the psychology factor. Whilst the facial action is comparatively steady because of the fixedness of the anatomic structure. Therefore, to improve performance of the action unit recognition will facilitate the facial expression recognition and provide profound basis for the mental state analysis, etc. However, it still a challenge job and recognition accuracy rate is limited, because the muscle movements around the face are tiny and the facial actions are not obvious accordingly. Taking account of the moving of muscles impact each other when person express their emotion, we propose to make full use of co-occurrence relationship among action units (AUs) in this paper. Considering the dynamic characteristic of AUs as well, we adopt the 3D Convolutional Neural Network(3DCNN) as base framework and proposed to recognize multiple action units around brows, nose and mouth specially contributing in the emotion expression with putting their co-occurrence relationships as constrain. The experiments have been conducted on a typical public dataset CASME and its variant CASME2 dataset. The experiment results show that our proposed AU co-occurrence constraint 3DCNN based AU recognition approach outperforms current approaches and demonstrate the effectiveness of taking use of AUs relationship in AU recognition.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
X. Jia, W. Li, Y. Wang, S. Hong, X. Su, "An Action Unit co-occurrence constraint 3DCNN based Action Unit recognition approach," KSII Transactions on Internet and Information Systems, vol. 14, no. 3, pp. 924-942, 2020. DOI: 10.3837/tiis.2020.03.001.

[ACM Style]
Xibin Jia, Weiting Li, Yuechen Wang, SungChan Hong, and Xing Su. 2020. An Action Unit co-occurrence constraint 3DCNN based Action Unit recognition approach. KSII Transactions on Internet and Information Systems, 14, 3, (2020), 924-942. DOI: 10.3837/tiis.2020.03.001.

[BibTeX Style]
@article{tiis:23380, title="An Action Unit co-occurrence constraint 3DCNN based Action Unit recognition approach", author="Xibin Jia and Weiting Li and Yuechen Wang and SungChan Hong and Xing Su and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2020.03.001}, volume={14}, number={3}, year="2020", month={March}, pages={924-942}}