中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Global-Attention-Based Neural Networks for Vision Language Intelligence

文献类型:期刊论文

作者Pei Liu; Yingjie Zhou; Dezhong Peng; Dapeng Wu
刊名IEEE/CAA Journal of Automatica Sinica
出版日期2021
卷号8期号:7页码:1243-1252
关键词Global attention image captioning latent contribution
ISSN号2329-9266
DOI10.1109/JAS.2020.1003402
英文摘要In this paper, we develop a novel global-attention-based neural network (GANN) for vision language intelligence, specifically, image captioning (language description of a given image). As many previous works, the encoder-decoder framework is adopted in our proposed model, in which the encoder is responsible for encoding the region proposal features and extracting global caption feature based on a specially designed module of predicting the caption objects, and the decoder generates captions by taking the obtained global caption feature along with the encoded visual features as inputs for each attention head of the decoder layer. The global caption feature is introduced for the purpose of exploring the latent contributions of region proposals for image captioning, and further helping the decoder better focus on the most relevant proposals so as to extract more accurate visual feature in each time step of caption generation. Our GANN is implemented by incorporating the global caption feature into the attention weight calculation phase in the word predication process in each head of the decoder layer. In our experiments, we qualitatively analyzed the proposed model, and quantitatively evaluated several state-of-the-art schemes with GANN on the MS-COCO dataset. Experimental results demonstrate the effectiveness of the proposed global attention mechanism for image captioning.
源URL[http://ir.ia.ac.cn/handle/173211/44579]  
专题自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式
GB/T 7714
Pei Liu,Yingjie Zhou,Dezhong Peng,et al. Global-Attention-Based Neural Networks for Vision Language Intelligence[J]. IEEE/CAA Journal of Automatica Sinica,2021,8(7):1243-1252.
APA Pei Liu,Yingjie Zhou,Dezhong Peng,&Dapeng Wu.(2021).Global-Attention-Based Neural Networks for Vision Language Intelligence.IEEE/CAA Journal of Automatica Sinica,8(7),1243-1252.
MLA Pei Liu,et al."Global-Attention-Based Neural Networks for Vision Language Intelligence".IEEE/CAA Journal of Automatica Sinica 8.7(2021):1243-1252.

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。