Cross matching of music and image
文献类型：会议论文
| 作者 | Xixuan Wu; Yu Qiao; Xiaogang Wang; Xiaoou Tang |
| 出版日期 | 2012 |
| 会议名称 | Proceedings of the 20th ACM international conference on Multimedia |
| 会议地点 | 美国 |
| 英文摘要 | Human perception of music and image are highly correlated. Both of them can inspire human sensation like emotion and power. This paper 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 with 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, and joint retrieval of music and image. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/3801]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2012 |
| 推荐引用方式 GB/T 7714 | Xixuan Wu,Yu Qiao,Xiaogang Wang,et al. Cross matching of music and image[C]. 见:Proceedings of the 20th ACM international conference on Multimedia. 美国. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。