Advanced Search
    Li Ang, Du Junping, Kou Feifei, Xue Zhe, Xu Xin, Xu Mingying, Jiang Yang. Scientific and Technological Information Oriented Semantics-Adversarial and Media-Adversarial Based Cross-Media Retrieval Method[J]. Journal of Computer Research and Development, 2023, 60(11): 2660-2670. DOI: 10.7544/issn1000-1239.202220430
    Citation: Li Ang, Du Junping, Kou Feifei, Xue Zhe, Xu Xin, Xu Mingying, Jiang Yang. Scientific and Technological Information Oriented Semantics-Adversarial and Media-Adversarial Based Cross-Media Retrieval Method[J]. Journal of Computer Research and Development, 2023, 60(11): 2660-2670. DOI: 10.7544/issn1000-1239.202220430

    Scientific and Technological Information Oriented Semantics-Adversarial and Media-Adversarial Based Cross-Media Retrieval Method

    • Cross-media retrieval of scientific and technological information is one of the important tasks in the cross-media study. Cross-media scientific and technological information retrieval obtains target information from massive multi-source and heterogeneous scientific and technological resources, which helps to design applications that meet users’ needs, including scientific and technological information recommendation, personalized scientific and technological information retrieval, etc. The core of cross-media retrieval is to learn a common subspace, in which data from different media can be directly compared with each other. In subspace learning, existing methods often focus on modeling the discrimination of intra-media data and the invariance of inter-media data after mapping, while ignoring semantic consistency within media and media discrimination within semantics, which limits the result of cross-media retrieval. In light of this, we propose a scientific and technological information oriented semantics-adversarial and media-adversarial cross-media retrieval method (SMCR) to find an effective common subspace. Specifically, SMCR minimizes the loss of inter-media semantic consistency in addition to modeling intra-media semantic discrimination, to preserve semantic similarity before and after mapping. Furthermore, SMCR constructs a basic feature mapping network and a refined feature mapping network to jointly minimize the media discriminative loss within semantics, to enhance the feature mapping network’s ability to confuse the media discriminant network. Experimental results on two datasets demonstrate that the proposed SMCR outperforms state-of-the-art methods in cross-media retrieval.
    • loading

    Catalog

      Turn off MathJax
      Article Contents

      /

      DownLoad:  Full-Size Img  PowerPoint
      Return
      Return