Embedded Files
In this stage, we used the same 200-item official music video dataset as in Lin's work [2] for the retrieval.
Video to Music Retrieved Results
Video to Music Retrieved Results
A higher score indicates a higher agreement.
Lin et al. [2]
Ours
Official Music Video
Results of Average Value
Lin et al. [2]
Ours
Official Music Video
Results of Average Value
Lin et al. [2]
Ours
Official Music Video
Results of Average Value
[2] Lin, Jen-Chun, Wen-Li Wei, and Hsin-Min Wang. "Automatic music video generation based on emotion-oriented pseudo song prediction and matching." Proceedings of the 24th ACM international conference on Multimedia. 2016.
Page updated
Report abuse