App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 5

Cross-modal retrieval based on object-level token reconstruction and textual entity awareness

Zhang Ming
Zeng Qingsong
Zheng Xinxuan
School of Computer Science & Engineering Artificial Intelligence, Wuhan Institute of Technology, Wuhan 430205, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0393

Abstract

Cross-modal semantic alignment serves as the foundation for image-text retrieval tasks. Existing approaches face distinct challenges: detector-based methods introduce computational burdens and error propagation, while patch-based Vision Transformers suffer from semantic ambiguity and redundancy that compromise object integrity. To address these limitations, we present a semantic-spatial fusion strategy that enables detector-free fine-grained alignment while preserving both semantic precision and spatial relationships. Our framework incorporates a visual calibration module that dynamically aggregates semantically consistent and spatially proximate patches into object-level tokens through dual constraints, complemented by entity-aware tokenization that maintains named entities as unified semantic units. Comprehensive experiments on Flickr30K and MS-COCO benchmarks demonstrate state-of-the-art performance, with rSum improving by 3-5 points in bidirectional retrieval tasks. This work establishes that semantic-spatial constrained token reconstruction effectively enhances alignment robustness and discrimination, advancing fine-grained cross-modal understanding.

Foundation Support

国家自然科学基金资助项目(62106180)
珠海市产学研合作项目(2320004002605)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0393
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 5

Publish History

[2026-01-19] Accepted Paper

Cite This Article

张明, 曾青松, 郑昕璇. 基于对象级Token重构与文本实体感知的跨模态检索 [J]. 计算机应用研究, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0393. (Zhang Ming, Zeng Qingsong, Zheng Xinxuan. Cross-modal retrieval based on object-level token reconstruction and textual entity awareness [J]. Application Research of Computers, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0393. )

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)