Micro-expression Recognition Challenge



  • Wen-Huang Cheng, National Chiao Tung University, Taiwan
  • Hong-Han Shuai, National Chiao Tung University, Taiwan
  • Hong-Xia Xie, National Chiao Tung University, Taiwan
  • Ling Lo, National Chiao Tung University, Taiwan
  • Kuang-Ting Chuang, OPPO Mobile, China
  • Su-Jing Wang , Institute of Psychology, Chinese Academy of Sciences
  • Moi Hoon Yap , Manchester Metropolitan University, UK
  • Tong Chen , Southwest University


As indicators of emotional states, interpreting people’s micro-expression correctly can boost many practical applications around our daily life, e.g., security and interrogation. However, micro-expression recognition is far from being solved due to insufficient annotation of the datasets. In this challenge, we propose a novel synthetic micro-expression dataset based on current manual annotated datasets. The provided dataset contains over 10,000 sequences with balanced classes and includes both training and testing part. 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!