App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 1

Referring video object segmentation based on Wavelet feature decoupling and cross-modal Fusion

She Xiangyang
Sun Furong
College of Artificial Intelligence & Computer Science, Xi'an University of Science and Technology, Xi'an 710600, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0140

Abstract

This paper proposes a referring video object segmentation method based on Wavelet Decoupling and Cross-modal Fusion Network (WDC-RVOS) to address the high-frequency signal loss and blurred object boundaries caused by progressive downsampling of visual features in referring video object segmentation. The proposed method introduces a redundant wavelet transform in the encoding stage to decouple visual features into a low-frequency semantic stream and a high-frequency edge stream, thereby reducing the loss of high-frequency boundary information. It further constructs a dual-stream cross-modal fusion mechanism to independently align and fuse these two types of features with textual features, achieving accurate object localization and detailed boundary representation. In the decoding stage, this paper designs an inverse wavelet decoder that predicts reconstruction coefficients in the wavelet domain and completes mask reconstruction through the inverse wavelet transform. Experimental results on four public datasets demonstrate that WDC-RVOS achieves favorable performance across multiple evaluation metrics. Specifically, WDC-RVOS achieves a J&F score of 60.4% on the Ref-YouTube-VOS dataset, validating the effectiveness of the proposed strategy in improving object boundary quality and segmentation performance.

Foundation Support

国家自然科学基金联合基金项目(U24A2092)
陕西省科技计划(2021JQ-576)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0140
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-08-28] Accepted Paper

Cite This Article

厍向阳, 孙芙蓉. 基于小波特征解耦与跨模态融合的指代视频目标分割 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0140. (She Xiangyang, Sun Furong. Referring video object segmentation based on Wavelet feature decoupling and cross-modal Fusion [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0140. )

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)