TY - JOUR
T1 - Short and long range relation based spatio-temporal transformer for micro-expression recognition
AU - Zhang, Liangfei
AU - Hong, Xiaopeng
AU - Arandjelovic, Ognjen
AU - Zhao, Guoying
N1 - Funding: The authors would like to thank the China Scholarship Council – University of St Andrews Scholarships (No.201908060250) funds L. Zhang for her PhD. This work is funded by the National Key Research and Development Project of China under Grant No. 2019YFB1312000, the National Natural Science Foundation of China under Grant No. 62076195, and the Fundamental Research Funds for the Central Universities under Grant No. AUGA5710011522.
PY - 2022/10/10
Y1 - 2022/10/10
N2 - Being spontaneous, micro-expressions are useful in the inference of a person's true emotions even if an attempt is made to conceal them. Due to their short duration and low intensity, the recognition of micro-expressions is a difficult task in affective computing. The early work based on handcrafted spatio-temporal features which showed some promise, has recently been superseded by different deep learning approaches which now compete for the state of the art performance. Nevertheless, the problem of capturing both local and global spatio-temporal patterns remains challenging. To this end, herein we propose a novel spatio-temporal transformer architecture – to the best of our knowledge, the first purely transformer based approach (i.e. void of any convolutional network use) for micro-expression recognition. The architecture comprises a spatial encoder which learns spatial patterns, a temporal aggregator for temporal dimension analysis, and a classification head. A comprehensive evaluation on three widely used spontaneous micro-expression data sets, namely SMIC-HS, CASME II and SAMM, shows that the proposed approach consistently outperforms the state of the art, and is the first framework in the published literature on micro-expression recognition to achieve the unweighted F1-score greater than 0.9 on any of the aforementioned data sets.
AB - Being spontaneous, micro-expressions are useful in the inference of a person's true emotions even if an attempt is made to conceal them. Due to their short duration and low intensity, the recognition of micro-expressions is a difficult task in affective computing. The early work based on handcrafted spatio-temporal features which showed some promise, has recently been superseded by different deep learning approaches which now compete for the state of the art performance. Nevertheless, the problem of capturing both local and global spatio-temporal patterns remains challenging. To this end, herein we propose a novel spatio-temporal transformer architecture – to the best of our knowledge, the first purely transformer based approach (i.e. void of any convolutional network use) for micro-expression recognition. The architecture comprises a spatial encoder which learns spatial patterns, a temporal aggregator for temporal dimension analysis, and a classification head. A comprehensive evaluation on three widely used spontaneous micro-expression data sets, namely SMIC-HS, CASME II and SAMM, shows that the proposed approach consistently outperforms the state of the art, and is the first framework in the published literature on micro-expression recognition to achieve the unweighted F1-score greater than 0.9 on any of the aforementioned data sets.
KW - Emotion recognition
KW - Long-term optical flow
KW - Self-attention mechanism
KW - Temporal aggregator
U2 - 10.1109/TAFFC.2022.3213509
DO - 10.1109/TAFFC.2022.3213509
M3 - Article
AN - SCOPUS:85139817909
SN - 1949-3045
VL - 13
SP - 1973
EP - 1985
JO - IEEE Transactions on Affective Computing
JF - IEEE Transactions on Affective Computing
IS - 4
ER -