Bridging Music and Image: A Preliminary Study with Multiple Ranking CCA Learning

Human perception of music and image are highly correlated. Both of them can inspire human sensation like emotion, power etc. This paper preliminarily investigates how to model the relationship between music and image using 47,888 music-image pairs extracted from music videos. We have two basic observations for this relationship: 1) music space exhibits simpler cluster structure than image space, and 2) the relationship between the two spaces is complex and nonlinear. Based on these observations, we develop Multiple Ranking Canonical Correlation Analysis (MR-CCA) to learn such relationship. MR-CCA clusters the music-image pairs according to their music parts, and then conducts Ranking CCA (R-CCA) for each cluster. Compared with classical CCA, R-CCA takes account of the pairwise ranking information available in our dataset. MR-CCA improves performance and significantly reduce computational cost. Experiment results show that R-CCA outperforms CCA, and MR-CCA has the best performance, a consistency score of 84.52% with human labeling. The proposed method can be generalized to model cross media relationship and has potential applications in video generation, background music recommendation etc.