Disclosed is a method and apparatus for recognizing a fine facial expression through deep run analysis of fine facial dynamics. The method for learning micro-facial expression according to an exemplary embodiment of the present invention includes the steps of extracting frames for predefined fine expressions in input video and generating a spatial learning model by learning spatial features of the extracted frames ; Extracting spatial features of all frames of the input video using the generated spatial learning model and generating temporal learning models using extracted spatial features for all of the frames, And learning each of the fine expressions.
展开▼