Disclosed are a method and apparatus for recognizing a fine expression through deep learning analysis of fine face dynamics. According to an exemplary embodiment of the present disclosure, a method of learning a fine facial expression extracts frames of predefined fine expressions from an input video, and generates a spatial learning model by learning spatial features of the extracted frames. ; And extracting a spatial feature of all frames of the input video using the generated spatial learning model, and generating a temporal learning model using the extracted spatial feature for all the frames. Learning each of the fine expressions.
展开▼