Image Annotation through Adaptive Dependency Fusion
Wang Fangxin(王方心)1,2; Liu Jie2; Zhang Shuwu2,3; Zhang Guixuan2; Zheng Yang2; Li Xiaoqian1,2
2018-12
会议名称IEEE International Conference on Progress in Informatics and Computing
会议日期2018-12
会议地点苏州
摘要

In order to improve the performance of image annotation, recently proposed methods build their model combining multiple dependencies from relations between image and label (image/label), between images (image/image) and between labels (label/label). However, most of these methods cannot make multiple dependencies work jointly, and their performances is largely depending on the results predicted by image/label dependency. To address this problem, we propose an end-to-
end image annotation model to associate these dependencies with the prediction path, which is composed of a series of labels in the order they are detected. Specially, our model can adaptively adjust the prediction path: from those easy-to-detect relevant labels to these hard-to-detect relevant ones. 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.

关键词Image Annotation Multiple Dependencies End-to-end Prediction Path
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/26112
专题数字内容技术与服务研究中心_版权智能与文化计算
通讯作者Liu Jie
作者单位1.中国科学院大学
2.中国科学院自动化研究所
3.北京电影学院,AICFVE
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Wang Fangxin,Liu Jie,Zhang Shuwu,et al. Image Annotation through Adaptive Dependency Fusion[C],2018.
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
037-036.pdf(503KB)会议论文 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
[Wang Fangxin(王方心)]的文章
[Liu Jie]的文章
[Zhang Shuwu]的文章
百度学术
百度学术中相似的文章
[Wang Fangxin(王方心)]的文章
[Liu Jie]的文章
[Zhang Shuwu]的文章
必应学术
必应学术中相似的文章
[Wang Fangxin(王方心)]的文章
[Liu Jie]的文章
[Zhang Shuwu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 037-036.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。