Journal Article

Emotion-Aware Music Driven Movie Montage

Liu, Wu-Qin, Xu, Chang-Sheng, Ma, Chong-Yang, Huang, Hai-Bin, Dong, Wei-Ming, Lin, Min-Xuan, Song, Yu

2023

Overview

In this paper, we present Emotion-Aware Music Driven Movie Montage, a novel paradigm for the challenging task of generating movie montages. Specifically, given a movie and a piece of music as the guidance, our method aims to generate a montage out of the movie that is emotionally consistent with the music. Unlike previous work such as video summarization, this task requires not only video content understanding, but also emotion analysis of both the input movie and music. To this end, we propose a two-stage framework, including a learning-based module for the prediction of emotion similarity and an optimization-based module for the selection and composition of candidate movie shots. The core of our method is to align and estimate emotional similarity between music clips and movie shots in a multi-modal latent space via contrastive learning. Subsequently, the montage generation is modeled as a joint optimization of emotion similarity and additional constraints such as scene-level story completeness and shot-level rhythm synchronization. We conduct both qualitative and quantitative evaluations to demonstrate that our method can generate emotionally consistent montages and outperforms alternative baselines.

• Publisher: Springer Nature Singapore,Springer,Springer Nature B.V
• Subject: Artificial Intelligence / Computer Science / Computer-generated imagery / Data Structures and Information Theory / Emotions / Information Systems Applications (incl.Internet) / Learning / Modules / Montage / Music / Optimization / Regular Paper / Similarity / Software Engineering / Synchronism / Theory of Computation / Video data