CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算
Cross-Domain Feature Learning in Multimedia
Yang, Xiaoshan; Zhang, Tianzhu; Xu, Changsheng; Xu CS(徐常胜)
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
2015-01
卷号17期号:1页码:64-78
摘要
In the Web 2.0 era, a huge number of media data,
such as text, image/video, and social interaction information,
have been generated on the social media sites (e.g., Facebook,
Google, Flickr, and YouTube). These media data can be effectively
adopted for many applications (e.g., image/video annotation,
image/video retrieval, and event classification) in multimedia.
However, it is difficult to design an effective feature representation
to describe these data because they have multi-modal property
(e.g., text, image, video, and audio) and multi-domain property
(e.g., Flickr, Google, and YouTube). To deal with these issues, we
propose a novel cross-domain feature learning (CDFL) algorithm
based on stacked denoising auto-encoders. By introducing the
modal correlation constraint and the cross-domain constraint
in conventional auto-encoder, our CDFL can maximize the
correlations among different modalities and extract domain invariant
semantic features simultaneously. To evaluate our CDFL
algorithm, we apply it to three important applications: sentiment
classification, spam filtering, and event classification. Comprehensive
evaluations demonstrate the encouraging performance of the
proposed approach.
关键词Cross-domain Deep Learning Feature Learning Multi-modal
DOI10.1109/TMM.2014.2375793
收录类别SCI
语种英语
引用统计
被引频次:100[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/11760
专题模式识别国家重点实验室_多媒体计算
通讯作者Xu CS(徐常胜)
作者单位中科院自动化研究所
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng,et al. Cross-Domain Feature Learning in Multimedia[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(1):64-78.
APA Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng,&徐常胜.(2015).Cross-Domain Feature Learning in Multimedia.IEEE TRANSACTIONS ON MULTIMEDIA,17(1),64-78.
MLA Yang, Xiaoshan,et al."Cross-Domain Feature Learning in Multimedia".IEEE TRANSACTIONS ON MULTIMEDIA 17.1(2015):64-78.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Cross-Domain Feature(3097KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
百度学术
百度学术中相似的文章
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
必应学术
必应学术中相似的文章
[Yang, Xiaoshan]的文章
[Zhang, Tianzhu]的文章
[Xu, Changsheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Cross-Domain Feature Learning in Multimedia(论文).pdf
格式: Adobe PDF
此文件暂不支持浏览
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。