MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation
This work addresses the challenge of cross-modal scene imagination from music for applications like video background music generation, representing an incremental improvement over prior music captioning models.
The paper tackles the problem of generating scene descriptions from music, called Music Scene Imagination (MSI), by introducing MusiScene, a model that improves upon existing music captioning by incorporating cross-modal video-audio data, and it demonstrates enhanced performance in generating contextually relevant captions compared to MU-LLaMA.
Humans can imagine various atmospheres and settings when listening to music, envisioning movie scenes that complement each piece. For example, slow, melancholic music might evoke scenes of heartbreak, while upbeat melodies suggest celebration. This paper explores whether a Music Language Model, e.g. MU-LLaMA, can perform a similar task, called Music Scene Imagination (MSI), which requires cross-modal information from video and music to train. To improve upon existing music captioning models which focusing solely on musical elements, we introduce MusiScene, a music captioning model designed to imagine scenes that complement each music. In this paper, (1) we construct a large-scale video-audio caption dataset with 3,371 pairs, (2) we finetune Music Understanding LLaMA for the MSI task to create MusiScene, and (3) we conduct comprehensive evaluations and prove that our MusiScene is more capable of generating contextually relevant captions compared to MU-LLaMA. We leverage the generated MSI captions to enhance Video Background Music Generation (VBMG) from text.