Micro-expression (ME) is a rapid, subtle and spontaneous motion of the human face that usually lasts between 1/25 and 1/5 seconds. Unlike macro-expression, which could be misleading on human emotion recognition, micro-expression is mostly expressed unconsciously where genuine emotion can be revealed. As indicators of emotional states, interpreting people's micro-expression correctlycan boost many practical applications around our daily life.
Dr. Letterman's team in the popular American drama "Lie to me" analyzes the inner characteristics of people based on micro-expressions, which has shown the charm of reading mind by microexpressions. The CVPR 2017 launched a Job Candidate Screening Coopetition, whose goal was helping both recruiters and job candidates building automatic recommendations based on multimedia clues, including micro-expressions . Recently, Apple's intelligent voice assistant Siri is aiming at recognizing facial expressions to interpret commands more accurately. China's largest insurer and financial services provider, Ping An Insurance Group Co. has applied micro-expressions recognition into fraud-detection to better assess the risk of remote loan applications4.The Gamma Lab launched a dessert shop that provides dessert by reading customers' micro-expression.
In the academic community, there have been several competitions held by international experts trying to solve the problem of micro-expression recognition, such as OMG2018, MEGC2018, MEGC2019, etc., but it is far from being solved due to insufficient annotation of the datasets. More samples are needed for robust automatic micro-expression recognition research and related applications. Also, the class imbalanced in the current database is a tough challenge for the recognition task. A dataset with a large size of even samples among classes is essential for a highlevel approach.
Considering the difficulties of fine-labeled ME dataset, we propose a novel synthetic ME dataset based on current manual annotated ME datasets, i.e., CASME II and SAMM, which contains over 10,000 sequences with balanced classes. We sincerely welcome the latest efforts and research advances from the scientific community to join this challenge in tackling the micro-expression recognition challenge on our published dataset!