In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 39, 2022 No. 4
1132-1136

Research on image captioning method based on sparse self-attention mechanism of integrated geometric relationship

Li Yan
Jin Xiaofeng
Intelligent Information Processing Laboratory, Yanbian University, Yanji Jilin 133002, China
DOI: 10.19734/j.issn.1001-3695.2021.07.0339

Abstract

Aiming at the problem that extracting visual features in image annotation task based on Transformer framework is easy to introduce noise, and in order to further improve the visual context information, this paper proposed an image captioning method based on comprehensive geometric relationship sparse self attention mechanism. Firstly, it combined the absolute position, relative position and spatial inclusion relationship of the image region to obtain a detailed and comprehensive visual representation so as to obtain the potential context information in the image. Secondly, this paper proposed the sparse method of attention layer weight matrix, which solved the problem that Transformer ignored the locality of image region and introduced noise information. Finally, this paper used the reinforcement learning method as the guidance strategy to optimize the target sequence at the sentence level. The experimental results on MS-COCO dataset show that the proposed method improves the baseline model by 0.2, 0.7, 0.1, 0.3, 1.2 and 0.4 respectively in BLEU1, BLEU4, METEOR, ROUGE-L, CIDEr and SPICE, which effectively improves the performance of image automatic captioning.

Foundation Support

延边大学世界一流学科建设培育项目(18YLPY14)
国家社会科学基金重大资助项目(18ZDA306)
延边大学外国语言文学世界一流学科建设攻关科研项目(18YLGG01)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2021.07.0339
Publish at: Application Research of Computers Printed Article, Vol. 39, 2022 No. 4
Section: Algorithm Research & Explore
Pages: 1132-1136
Serial Number: 1001-3695(2022)04-029-1132-05

Publish History

[2021-11-15] Accepted Paper
[2022-04-05] Printed Article

Cite This Article

李艳, 金小峰. 基于综合几何关系稀疏自注意力机制的图像标注方法研究 [J]. 计算机应用研究, 2022, 39 (4): 1132-1136. (Li Yan, Jin Xiaofeng. Research on image captioning method based on sparse self-attention mechanism of integrated geometric relationship [J]. Application Research of Computers, 2022, 39 (4): 1132-1136. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)