In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 7

Reverse-focus fine-grained multimodal semantic alignment for video captioning

Cai Xia
Luo Huilan
Wan Siqi
School of Information Engineering, Jiangxi University of Technology, Ganzhou Jiangxi 341100, China
DOI: 10.19734/j.issn.1001-3695.2024.11.0492

Abstract

Existing video captioning often introduce multimodal information to assist models in extracting critical and fine-grained details from complex and dynamic visual content. However, these methods tend to overlook the semantic gaps caused by representational differences among modalities. To bridge these gaps, facilitate effective cross-modal alignment and efficient fusion, and enhance the extraction of fine-grained semantic information, this paper proposed a Reverse-Focus Fine-Grained Multimodal Semantic Alignment for Video Captioning (RM4Cap) . This model combined an image-text pair corpus and facilitated semantic alignment between video and image, indirectly aligning video representations with text in the image-text pairs. And designed a reverse attention focusing algorithm to suppress redundant scene information while highlighting inconspicuous objects and their interactions. Experiments conducted on the MSVD and MSRVTT datasets show that the model significantly outperforms existing methods in metrics such as CIDEr and BLEU-4. It effectively resolves the alignment challenges and redundancy issues in multimodal fusion, further demonstrating its ability to narrow the cross-modal semantic gap.

Foundation Support

国家自然科学基金资助项目(62361032)
江西省主要学科技术带头人领军人才计划资助项目(20213BCJ22004)
江西省自然科学基金重点项目(20232ACB202011)
多维智能感知与控制江西省重点实验室(2024SSY03161)
江西省研究生创新专项资金项目(YC2023-S657)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.11.0492
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 7

Publish History

[2025-03-14] Accepted Paper

Cite This Article

蔡霞, 罗会兰, 万斯奇. 反向聚焦细粒度多模态语义对齐的视频字幕模型 [J]. 计算机应用研究, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.11.0492. (Cai Xia, Luo Huilan, Wan Siqi. Reverse-focus fine-grained multimodal semantic alignment for video captioning [J]. Application Research of Computers, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.11.0492. )

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)