BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yutong, Wang, Yunke, Chen, Xinyuan, Xu, Chang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911720396554240
author Wang, Yutong
Wang, Yunke
Chen, Xinyuan
Xu, Chang
author_facet Wang, Yutong
Wang, Yunke
Chen, Xinyuan
Xu, Chang
contents Automatic movie trailer generation must select shots from a full-length film and synchronize them with background music. Existing methods either relegate music alignment to post-processing or enforce rigid one-to-one shot-music mappings, overlooking that professional editing rhythm is elastic: rapid cuts accompany high-energy passages while sustained shots span quieter bars. We introduce BEAT, a framework that addresses this gap with two core components: MuVA, a compact music-visual alignment encoder trained with Sinkhorn-regularized two-stage learning, and Bar-DP, an energy-adaptive dynamic programming algorithm that produces elastic many-to-one alignments following musical dynamics. These components are integrated into a five-phase agentic pipeline that grounds the core alignment in learned cross-modal features while coordinating higher-level creative decisions through structured text signals. To support comprehensive evaluation, we also introduce TrailerArena, a benchmark with 20+ metrics across four complementary dimensions. On TrailerArena, BEAT achieves state-of-the-art performance across shot selection, ordering, and perceptual quality, while producing fully composed trailers end-to-end.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27067
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation
Wang, Yutong
Wang, Yunke
Chen, Xinyuan
Xu, Chang
Computer Vision and Pattern Recognition
Automatic movie trailer generation must select shots from a full-length film and synchronize them with background music. Existing methods either relegate music alignment to post-processing or enforce rigid one-to-one shot-music mappings, overlooking that professional editing rhythm is elastic: rapid cuts accompany high-energy passages while sustained shots span quieter bars. We introduce BEAT, a framework that addresses this gap with two core components: MuVA, a compact music-visual alignment encoder trained with Sinkhorn-regularized two-stage learning, and Bar-DP, an energy-adaptive dynamic programming algorithm that produces elastic many-to-one alignments following musical dynamics. These components are integrated into a five-phase agentic pipeline that grounds the core alignment in learned cross-modal features while coordinating higher-level creative decisions through structured text signals. To support comprehensive evaluation, we also introduce TrailerArena, a benchmark with 20+ metrics across four complementary dimensions. On TrailerArena, BEAT achieves state-of-the-art performance across shot selection, ordering, and perceptual quality, while producing fully composed trailers end-to-end.
title BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.27067