Automated Generation of Movie Tributes
This thesis’s purpose is to generate a movie tribute in the form of a videoclip for a given movie and music. A videoclip is considered to be a video containing the most important clips from the movie and a music playing in the background. The most important clips are collected by summarizing the movie subtitles with Support Sets algorithm. It is important that the artifact is coherent and fluid, hence there is the need to balance between the selection of important content and the selection of content that is in harmony with the music. To achieve so, clips are filltered so as to ensure that only those that contain the same emotion as the music are chosen to appear in the final video. This is made by extracting emotion related audio features from their corresponding scenes and from the music, and then comparing them by calculating the cosine distance. Filtered clips fill the music length in a chronological order.