Music Grounding by Short Video

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xin, Zijie, Wang, Minquan, Liu, Jingyu, Ma, Ye, Chen, Quan, Jiang, Peng, Li, Xirong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913949074587648
author Xin, Zijie
Wang, Minquan
Liu, Jingyu
Ma, Ye
Chen, Quan
Jiang, Peng
Li, Xirong
author_facet Xin, Zijie
Wang, Minquan
Liu, Jingyu
Ma, Ye
Chen, Quan
Jiang, Peng
Li, Xirong
contents Adding proper background music helps complete a short video to be shared. Previous work tackles the task by video-to-music retrieval (V2MR), aiming to find the most suitable music track from a collection to match the content of a given query video. In practice, however, music tracks are typically much longer than the query video, necessitating (manual) trimming of the retrieved music to a shorter segment that matches the video duration. In order to bridge the gap between the practical need for music moment localization and V2MR, we propose a new task termed Music Grounding by Short Video (MGSV). To tackle the new task, we introduce a new benchmark, MGSV-EC, which comprises a diverse set of 53k short videos associated with 35k different music moments from 4k unique music tracks. Furthermore, we develop a new baseline method, MaDe, which performs both video-to-music matching and music moment detection within a unified end-to-end deep network. Extensive experiments on MGSV-EC not only highlight the challenging nature of MGSV but also set MaDe as a strong baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Music Grounding by Short Video
Xin, Zijie
Wang, Minquan
Liu, Jingyu
Ma, Ye
Chen, Quan
Jiang, Peng
Li, Xirong
Multimedia
Adding proper background music helps complete a short video to be shared. Previous work tackles the task by video-to-music retrieval (V2MR), aiming to find the most suitable music track from a collection to match the content of a given query video. In practice, however, music tracks are typically much longer than the query video, necessitating (manual) trimming of the retrieved music to a shorter segment that matches the video duration. In order to bridge the gap between the practical need for music moment localization and V2MR, we propose a new task termed Music Grounding by Short Video (MGSV). To tackle the new task, we introduce a new benchmark, MGSV-EC, which comprises a diverse set of 53k short videos associated with 35k different music moments from 4k unique music tracks. Furthermore, we develop a new baseline method, MaDe, which performs both video-to-music matching and music moment detection within a unified end-to-end deep network. Extensive experiments on MGSV-EC not only highlight the challenging nature of MGSV but also set MaDe as a strong baseline.
title Music Grounding by Short Video
topic Multimedia
url https://arxiv.org/abs/2408.16990