中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Emotion-Aware Music Driven Movie Montage

文献类型：期刊论文

作者Liu, Wu-Qin3,4; Lin, Min-Xuan2; Huang, Hai-Bin2; Ma, Chong-Yang2; Song, Yu1; Dong, Wei-Ming3; Xu, Chang-Sheng3
刊名JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
出版日期2023-06-01
卷号38期号:3页码:540-553
ISSN号1000-9000
关键词movie montage emotion analysis audio-visual modality contrastive learning
DOI10.1007/s11390-023-3064-6
通讯作者Dong, Wei-Ming(weiming.dong@ia.ac.cn)
英文摘要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.
资助项目National Key Research and Development Program of China[2020AAA0106200] ; National Natural Science Foundation of China[61832016]
WOS研究方向Computer Science
语种英语
出版者SPRINGER SINGAPORE PTE LTD
WOS记录号WOS:001089311400006
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/54469]  
专题多模态人工智能系统全国重点实验室
通讯作者Dong, Wei-Ming
作者单位1.Univ Sci & Technol Beijing, Sch Mech Engn, Beijing 100083, Peoples R China
2.Kuaishou Technol, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Wu-Qin,Lin, Min-Xuan,Huang, Hai-Bin,et al. Emotion-Aware Music Driven Movie Montage[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2023,38(3):540-553.
APA Liu, Wu-Qin.,Lin, Min-Xuan.,Huang, Hai-Bin.,Ma, Chong-Yang.,Song, Yu.,...&Xu, Chang-Sheng.(2023).Emotion-Aware Music Driven Movie Montage.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,38(3),540-553.
MLA Liu, Wu-Qin,et al."Emotion-Aware Music Driven Movie Montage".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 38.3(2023):540-553.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。