Cross-Modal Learning for Music-to-Music-Video Description Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mao, Zhuoyuan, Zhao, Mengjie, Wu, Qiyu, Zhong, Zhi, Liao, Wei-Hsiang, Wakaki, Hiromi, Mitsufuji, Yuki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913736043790336
author Mao, Zhuoyuan
Zhao, Mengjie
Wu, Qiyu
Zhong, Zhi
Liao, Wei-Hsiang
Wakaki, Hiromi
Mitsufuji, Yuki
author_facet Mao, Zhuoyuan
Zhao, Mengjie
Wu, Qiyu
Zhong, Zhi
Liao, Wei-Hsiang
Wakaki, Hiromi
Mitsufuji, Yuki
contents Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models has opened a promising pathway for music-video (MV) generation by first addressing the music-to-MV description task and subsequently leveraging these models for video generation. In this study, we focus on the MV description generation task and propose a comprehensive pipeline encompassing training data construction and multimodal model fine-tuning. We fine-tune existing pre-trained multimodal models on our newly constructed music-to-MV description dataset based on the Music4All dataset, which integrates both musical and visual information. Our experimental results demonstrate that music representations can be effectively mapped to textual domains, enabling the generation of meaningful MV description directly from music inputs. We also identify key components in the dataset construction pipeline that critically impact the quality of MV description and highlight specific musical attributes that warrant greater focus for improved MV description generation.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11190
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Modal Learning for Music-to-Music-Video Description Generation
Mao, Zhuoyuan
Zhao, Mengjie
Wu, Qiyu
Zhong, Zhi
Liao, Wei-Hsiang
Wakaki, Hiromi
Mitsufuji, Yuki
Sound
Artificial Intelligence
Computation and Language
Multimedia
Audio and Speech Processing
Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models has opened a promising pathway for music-video (MV) generation by first addressing the music-to-MV description task and subsequently leveraging these models for video generation. In this study, we focus on the MV description generation task and propose a comprehensive pipeline encompassing training data construction and multimodal model fine-tuning. We fine-tune existing pre-trained multimodal models on our newly constructed music-to-MV description dataset based on the Music4All dataset, which integrates both musical and visual information. Our experimental results demonstrate that music representations can be effectively mapped to textual domains, enabling the generation of meaningful MV description directly from music inputs. We also identify key components in the dataset construction pipeline that critically impact the quality of MV description and highlight specific musical attributes that warrant greater focus for improved MV description generation.
title Cross-Modal Learning for Music-to-Music-Video Description Generation
topic Sound
Artificial Intelligence
Computation and Language
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2503.11190