中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Image captioning via hierarchical attention mechanism and policy gradient optimization

文献类型:期刊论文

作者Yan, Shiyang2; Xie, Yuan1,3,4,6; Wu, Fangyu5,7; Smith, Jeremy S.5; Lu, Wenjin7; Zhang, Bailing3,4
刊名SIGNAL PROCESSING
出版日期2020-02-01
卷号167页码:12
ISSN号0165-1684
关键词Image captioning Hierarchical attention mechanism Generative adversarial network Reinforcement learning Policy gradient
DOI10.1016/j.sigpro.2019.107329
通讯作者Yan, Shiyang(shiyang.yan@qub.ac.uk)
英文摘要Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the successful deep learning models, especially the CNN model and Long Short Term Memories (LSTMs) with attention mechanism, we propose a hierarchical attention model by utilizing both of the global CNN features and the local object features for more effective feature representation and reasoning in image captioning. The generative adversarial network (GAN), together with a reinforcement learning (RL) algorithm, is applied to solve the exposure bias problem in RNN-based supervised training for language problems. In addition, through the automatic measurement of the consistency between the generated caption and the image content by the discriminator in the GAN framework and RL optimization, we make the finally generated sentences more accurate and natural. Comprehensive experiments show the improved performance of the hierarchical attention mechanism and the effectiveness of our RL-based optimization method. Our model achieves state-of-the-art results on several important metrics in the MSCOCO dataset, using only greedy inference. (C) 2019 Elsevier B.V. All rights reserved.
WOS关键词NETWORKS
WOS研究方向Engineering
语种英语
出版者ELSEVIER
WOS记录号WOS:000497600200030
源URL[http://ir.ia.ac.cn/handle/173211/29387]  
专题自动化研究所_精密感知与控制研究中心
通讯作者Yan, Shiyang
作者单位1.East China Normal Univ, Sch Comp Sci & Software Engn, Shanghai, Peoples R China
2.Queens Univ Belfast, Sch Elect Elect Engn & Comp Sci, Belfast, Antrim, North Ireland
3.Inst Adv Artificial Intelligence Nanjing, Nanjing, Jiangsu, Peoples R China
4.Horizon Robot, Beijing, Peoples R China
5.Univ Liverpool, Elect Engn & Elect, Liverpool, Merseyside, England
6.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
7.Xian Jiaotong Liverpool Univ, Dept Comp Sci & Software Engn, Suzhou, Peoples R China
推荐引用方式
GB/T 7714
Yan, Shiyang,Xie, Yuan,Wu, Fangyu,et al. Image captioning via hierarchical attention mechanism and policy gradient optimization[J]. SIGNAL PROCESSING,2020,167:12.
APA Yan, Shiyang,Xie, Yuan,Wu, Fangyu,Smith, Jeremy S.,Lu, Wenjin,&Zhang, Bailing.(2020).Image captioning via hierarchical attention mechanism and policy gradient optimization.SIGNAL PROCESSING,167,12.
MLA Yan, Shiyang,et al."Image captioning via hierarchical attention mechanism and policy gradient optimization".SIGNAL PROCESSING 167(2020):12.

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。