App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 12

Weakly supervised 3d visual grounding via prompt-guided knowledge consolidation

Dong Haorana,b
Chen Zhena,b
Deng Xudonga,b
Mi Jinpenga
Liu Dana
a. Institute of Machine Intelligence, b. School of Health Science and Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0102

Abstract

Weakly supervised 3D visual grounding aims to locate target objects in 3D scenarios based on referring expressions. The challenge lies in achieving region-level predictions relying solely on scene-level training annotations. Existing state-of-the-art (SOTA) models mainly focus on sentence-level cross-modal matching, neglecting the exploration of fine-grained semantics such as noun phrases, which leads to target ambiguity. To address this issue, this paper proposed PGKC, a neat yet effective framework. The framework utilizes a noun phrase-guided prompt construction module and leverages a pre-trained large-scale model to generate semantically aligned prompts to enhance the original referring semantics. Furthermore, the framework incorporates a prompt-guided knowledge consolidation block, which consists of a prompt-aware fused feature augmentation module and a Transformer encoder, to capture more discriminative visual contexts and augment multi-modal correlation knowledge. Finally, the algorithm feeds the consolidated visual and textual representations into a grounding head to accomplish cross-modal matching. Experimental results show that PGKC improves the average accuracy on the ScanRefer, Nr3D and Sr3D datasets by 1.02%, 1.96% and 0.90% respectively, significantly enhancing the accuracy and robustness of visual grounding in complex 3D scenarios.

Foundation Support

国家自然科学基金资助项目(62106026,62272170,42130112)
上海市自然科学基金资助项目(23ZR1419300)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0102
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 12

Publish History

[2026-08-12] Accepted Paper

Cite This Article

董皓然, 陈桢, 邓旭东, 等. 基于提示引导知识增强的弱监督3D指称表达理解 [J]. 计算机应用研究, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0102. (Dong Haoran, Chen Zhen, Deng Xudong, et al. Weakly supervised 3d visual grounding via prompt-guided knowledge consolidation [J]. Application Research of Computers, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0102. )

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)