A subjective evaluation was conducted to compare further the retrieved results of using the proposed method with the other methods. Forty participants (15 male and 25 female) were recruited from a social platform to watch a retrieved music-video questionnaire. In the questionnaire, four stages of questions were used to evaluate the efficiency of the proposed method.
Hm: High-level Representation of Music Modality; Hv: High-level Representation of Video Modality
Cm: Common Representation of Music Modality; Cv: Common Representation of Video Modality