OPT OpenIR  > 光学影像学习与分析中心
Image2song: Song Retrieval via Bridging Image Content and Lyric Words
Li, Xuelong1; Hu, Di2; Lu, Xiaoqiang1
2017-12-22
会议名称16th IEEE International Conference on Computer Vision, ICCV 2017
会议录名称Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
卷号2017-October
页码5650-5659
会议日期2017-10-22
会议地点Venice, Italy
出版者Institute of Electrical and Electronics Engineers Inc.
产权排序1
摘要

Image is usually taken for expressing some kinds of emotions or purposes, such as love, celebrating Christmas. There is another better way that combines the image and relevant song to amplify the expression, which has drawn much attention in the social network recently. Hence, the automatic selection of songs should be expected. In this paper, we propose to retrieve semantic relevant songs just by an image query, which is named as the image2song problem. Motivated by the requirements of establishing correlation in semantic/content, we build a semantic-based song retrieval framework, which learns the correlation between image content and lyric words. This model uses a convolutional neural network to generate rich tags from image regions, a recurrent neural network to model lyric, and then establishes correlation via a multi-layer perceptron. To reduce the content gap between image and lyric, we propose to make the lyric modeling focus on the main image content via a tag attention. We collect a dataset from the social-sharing multimodal data to study the proposed problem, which consists of (image, music clip, lyric) triplets. We demonstrate that our proposed model shows noticeable results in the image2song retrieval task and provides suitable songs. Besides, the song2image task is also performed. © 2017 IEEE.

作者部门光学影像学习与分析中心
DOI10.1109/ICCV.2017.602
收录类别EI ; ISTP
ISBN号9781538610329
语种英语
ISSN号15505499
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/29942
专题光学影像学习与分析中心
作者单位1.Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, 710119, China
2.School of Computer Science, Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, 710072, China
推荐引用方式
GB/T 7714
Li, Xuelong,Hu, Di,Lu, Xiaoqiang. Image2song: Song Retrieval via Bridging Image Content and Lyric Words[C]:Institute of Electrical and Electronics Engineers Inc.,2017:5650-5659.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Image2song Song Retr(1295KB)会议论文 开放获取CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Xuelong]的文章
[Hu, Di]的文章
[Lu, Xiaoqiang]的文章
百度学术
百度学术中相似的文章
[Li, Xuelong]的文章
[Hu, Di]的文章
[Lu, Xiaoqiang]的文章
必应学术
必应学术中相似的文章
[Li, Xuelong]的文章
[Hu, Di]的文章
[Lu, Xiaoqiang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。