Journal of Qingdao University(Engineering & Technology Edition), Volume. 40, Issue 2, 11(2025)

Open-world Multidimensional Feature Fusion Scene Graph Generation

GU Feifan1, ZHOU Mengmeng2, SONG Shimiao1, GE Jiashang1, and YANG Jie1、*
Author Affiliations
  • 1College of Mechanical and Electrical Engineering, Qingdao University, Qingdao 266071, China
  • 2Qingdao QCIT Technology Co., Ltd., Qingdao 266100, China
  • show less

    The open-world scene graph generation task has difficulty in detecting unknown objects and their relationships. To address this issue, a relation-reasoning model based on multidimensional feature fusion (MDFF) is proposed. The proposed model is combined with an open-world object detector to form a two-stage open-world scene graph generation algorithm. First, the pretrained open-world object detector identifies objects in the input images. The MDFF model then performs relationship inference based on the detection results. Comparative experiments are conducted on the VG 150 dataset using traditional methods and the MDFF model. The experimental results indicate that the MDFF model achieves 7% improvement in recall rate for predicate classification tasks. Moreover, the performance improves by 3% in open-world scene graph generation and zero-shot inference tasks. Furthermore, ablation studies have confirmed the effectiveness of different feature dimensions on model performance improvement.

    Tools

    Get Citation

    Copy Citation Text

    GU Feifan, ZHOU Mengmeng, SONG Shimiao, GE Jiashang, YANG Jie. Open-world Multidimensional Feature Fusion Scene Graph Generation[J]. Journal of Qingdao University(Engineering & Technology Edition), 2025, 40(2): 11

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Feb. 28, 2025

    Accepted: Aug. 22, 2025

    Published Online: Aug. 22, 2025

    The Author Email: YANG Jie (yangjie@qdu.edu.cn)

    DOI:10.13306/j.1006-9798.2025.02.002

    Topics