Inductive Zero-Shot Image Annotation via Embedding Graph
Wang, Fangxin1,2; Liu, Jie1; Zhang, Shuwu1,3; Zhang, Guixuan1; Li, Yuejun1,2; Yuan, Fei1
发表期刊IEEE ACCESS
ISSN2169-3536
2019
卷号7页码:107816-107830
通讯作者Liu, Jie(jie.liu@ia.ac.cn)
摘要Conventional image annotation systems can only handle those images having labels within the exist library, but cannot recognize those novel labels. In order to learn new concepts, one has to gather large amount of labeled images and train the model from scratch. More importantly, it can come with a high price to collect those labeled images. For these reasons, we put forward a zero-shot image annotation model, to reduce the demand for the images with novel labels. In this paper, we focus on the two big challenges of zero-shot image annotation: polysemous words and a strong bias in the generalized zero-shot setting. For the first problem, instead of training on large corpus datasets as previous methods, we propose to adopt Node2Vec to obtain contextualized word embeddings, which can easily produce word vectors of the polysemous words. For the second problem, we alleviate the strong bias in two ways: on one hand, we utilize a model based on graph convolutional network (GCN) to make target images involved in the training process; on the other hand, we put forward a novel semantic coherent (SC) loss to capture the semantic relations of the source and target labels. The extensive experiments on NUSWIDE, COCO, IAPR TC-12, and Core15k datasets show the superiority of the proposed model and the annotation performance get improved by 4%-6% comparing with state-of-the-art methods.
关键词Contextualized word embeddings graph convolutional network image annotation Node2Vec zero-shot
DOI10.1109/ACCESS.2019.2925383
收录类别SCI
语种英语
资助项目National Key R&D Program of China[2018YFC0809200] ; National Key Research and Development Plan[61602480] ; National Key R&D Program of China[2018YFC0809200] ; National Key Research and Development Plan[61602480]
项目资助者National Key R&D Program of China ; National Key Research and Development Plan
WOS研究方向Computer Science ; Engineering ; Telecommunications
WOS类目Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号WOS:000481980800008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类多模态智能
引用统计
被引频次:3[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/173211/26113
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.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Beijing Film Acad, AICFVE, Beijing, Peoples R China
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. Inductive Zero-Shot Image Annotation via Embedding Graph[J]. IEEE ACCESS,2019,7:107816-107830.
APA Wang, Fangxin,Liu, Jie,Zhang, Shuwu,Zhang, Guixuan,Li, Yuejun,&Yuan, Fei.(2019).Inductive Zero-Shot Image Annotation via Embedding Graph.IEEE ACCESS,7,107816-107830.
MLA Wang, Fangxin,et al."Inductive Zero-Shot Image Annotation via Embedding Graph".IEEE ACCESS 7(2019):107816-107830.
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
FINAL Article.pdf(1472KB)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
[Wang, Fangxin]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]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]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: FINAL Article.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。