Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.05894 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915377344151552 |
|---|---|
| author | Izzati, Fathinah Li, Xinyue Wu, Yuxuan Xia, Gus |
| author_facet | Izzati, Fathinah Li, Xinyue Wu, Yuxuan Xia, Gus |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05894 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation Izzati, Fathinah Li, Xinyue Wu, Yuxuan Xia, Gus Artificial Intelligence Computation and Language 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. |
| title | MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2507.05894 |