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. 数字内容技术与服务研究中心
  5. 新媒体服务与管理技术
Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion

文献类型：期刊论文

作者Wang, Fangxin1,2; Liu, Jie1; Zhang, Shuwu1,3; Zhang, Guixuan1; Zheng, Yang1; Li, Xiaoqian1,2; Liang, Wei1; Li, Yuejun1,2
刊名KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
出版日期2019-09-30
卷号13期号:9页码:4665-4683
关键词image annotation multiple dependencies self-attention prediction path Triplet Margin loss
ISSN号1976-7277
DOI10.3837/tiis.2019.09.019
通讯作者Liu, Jie(jie.liu@ia.ac.cn)
英文摘要Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.
WOS关键词AUTOMATIC IMAGE ANNOTATION
资助项目National Key R&D Program of China[2017YFB1401000] ; Key Laboratory of Digital Rights Services, is one of the National Science and Standardization Key Labs for Press and Publication Industry
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000488294100019
出版者KSII-KOR SOC INTERNET INFORMATION
资助机构National Key R&D Program of China ; Key Laboratory of Digital Rights Services, is one of the National Science and Standardization Key Labs for Press and Publication Industry
源URL[http://ir.ia.ac.cn/handle/173211/26114]  
专题数字内容技术与服务研究中心_新媒体服务与管理技术
通讯作者Liu, Jie
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Beijing Film Acad, AICFVE, Beijing 100088, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Fangxin,Liu, Jie,Zhang, Shuwu,et al. Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion[J]. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,2019,13(9):4665-4683.
APA Wang, Fangxin.,Liu, Jie.,Zhang, Shuwu.,Zhang, Guixuan.,Zheng, Yang.,...&Li, Yuejun.(2019).Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion.KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,13(9),4665-4683.
MLA Wang, Fangxin,et al."Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion".KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 13.9(2019):4665-4683.

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。