This application provides a video similarity detection method, relates to the field of artificial intelligence, and specifically relates to computer vision. The method includes: A detection apparatus receives a first video, and determines a key frame of the first video based on the first video; inputs the key frame to a feature extraction model to obtain a feature of the key frame; determines a similar key frame and a second video based on the feature of the key frame, where the first video is a to-be-detected video, and the second video is a video, in a video library, that is similar to the first video; and further inputs the key frame and the similar key frame to an editing type recognition model to obtain an editing type, where the editing type indicates an editing type used for editing between the first video and the second video. The feature extraction model and the editing type recognition model are separately different based on neural network models. According to this method, the similar video corresponding to the to-be-detected video can be more accurately determined, and the type of editing performed on the to-be-detected video compared with the similar video is further obtained.