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
  5. 多媒体计算与图形学团队
Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach

文献类型：期刊论文

作者Yuan, Zhaoquan1; Xu, Changsheng1; Sang, Jitao1; Yan, Shuicheng2; Hossain, M. Shamim3
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2015-06-01
卷号17期号:6页码:816-827
关键词Auto-encoder deep learning hierarchical feature learning social tags
英文摘要Feature representation learning is an important and fundamental task in multimedia and pattern recognition research. In this paper, we propose a novel framework to explore the hierarchical structure inside the images from the perspective of feature representation learning, which is applied to hierarchical image annotation. Different from the current trend in multimedia analysis of using pre-defined features or focusing on the end-task "flat" representation, we propose a novel layer-wise tag-embedded deep learning (LTDL) model to learn hierarchical features which correspond to hierarchical semantic structures in the tag hierarchy. Unlike most existing deep learning models, LTDL utilizes both the visual content of the image and the hierarchical information of associated social tags. In the training stage, the two kinds of information are fused in a bottom-up way. Supervised training and multi-modal fusion alternate in a layer-wise way to learn feature hierarchies. To validate the effectiveness of LTDL, we conduct extensive experiments for hierarchical image annotation on a large-scale public dataset. Experimental results show that the proposed LTDL can learn representative features with improved performances.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
研究领域[WOS]Computer Science ; Telecommunications
关键词[WOS]CLASSIFICATION ; MULTIMEDIA ; MODELS ; REPRESENTATION ; RECOGNITION ; DICTIONARY ; MULTIPLE ; DATABASE
收录类别SCI
语种英语
WOS记录号WOS:000354527500005
公开日期2015-09-22
源URL[http://ir.ia.ac.cn/handle/173211/8079]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 119077, Singapore
3.King Saud Univ, SWE Dept, Coll Comp & Informat Sci, Riyadh 11543, Saudi Arabia
推荐引用方式
GB/T 7714		 Yuan, Zhaoquan,Xu, Changsheng,Sang, Jitao,et al. Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(6):816-827.
APA Yuan, Zhaoquan,Xu, Changsheng,Sang, Jitao,Yan, Shuicheng,&Hossain, M. Shamim.(2015).Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach.IEEE TRANSACTIONS ON MULTIMEDIA,17(6),816-827.
MLA Yuan, Zhaoquan,et al."Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach".IEEE TRANSACTIONS ON MULTIMEDIA 17.6(2015):816-827.

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。