Overview of indoor scene recognition and representation methods based on multimodal knowledge graphs

被引:0
|
作者
Li, Jianxin [1 ]
Si, Guannan [1 ]
Tian, Pengxin [1 ]
An, Zhaoliang [1 ]
Zhou, Fengyu [2 ]
机构
[1] Shandong Jiaotong Univ, Sch Informat Sci & Elect Engn, Changqing Univ Sci Pk, Jinan 250357, Peoples R China
[2] Shandong Univ, Sch Control Sci & Engn, 17923 Jingshi Rd, Jinan 250061, Shandong, Peoples R China
基金
中国国家自然科学基金;
关键词
Knowledge graph; Scene graph; Neural network; Indoor entity recognition; IMAGE FUSION; PIXEL-LEVEL; ATTENTION; NETWORKS; SCALE;
D O I
10.1007/s10489-023-05235-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper provides a comprehensive overview of multi-modal knowledge graph technology and a three-layer framework for scene recognition. Integrating diverse 3D expertise into a deep neural network enhances scene cognition and knowledge representation. Real-time 3D scene graph construction via feature matching is explored, demonstrating the feasibility of effective scene knowledge representation. Leveraging advanced multimodal knowledge graph and scene recognition, the paper presents a promising avenue for AI-driven scene cognition and construction. It contributes to understanding multi-modal knowledge graph technology's potential in addressing scene recognition challenges and implications for future advancements. This interdisciplinary work establishes a foundation for intelligent scene analysis and interpretation.
引用
收藏
页码:899 / 923
页数:25
相关论文
共 50 条
  • [1] Overview of indoor scene recognition and representation methods based on multimodal knowledge graphs
    Jianxin Li
    Guannan Si
    Pengxin Tian
    Zhaoliang An
    Fengyu Zhou
    Applied Intelligence, 2024, 54 : 899 - 923
  • [2] Survey of 3D Scene Recognition and Representation Methods of Multimodal Knowledge
    Li, Jianxin
    Si, Guannan
    Tian, Pengxin
    An, Zhaoliang
    Zhou, Fengyu
    Computer Engineering and Applications, 2023, 59 (20) : 35 - 50
  • [3] Indoor Scene Recognition Based On Deep Learning And Sparse Representation
    Sun, Ning
    Zhu, Xiaoying
    Liu, Jixin
    Han, Guang
    2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2017, : 844 - 849
  • [4] A Discriminative Representation of Convolutional Features for Indoor Scene Recognition
    Khan, Salman H.
    Hayat, Munawar
    Bennamoun, Mohammed
    Togneri, Roberto
    Sohel, Ferdous A.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (07) : 3372 - 3383
  • [5] Multimodal Data Enhanced Representation Learning for Knowledge Graphs
    Wang, Zikang
    Li, Linjing
    Li, Qiudan
    Zeng, Daniel
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [6] Representation learning of knowledge graphs with correlation-based methods
    Sabet, Maryam
    Pajoohan, MohammadReza
    Moosavi, Mohammad R.
    INFORMATION SCIENCES, 2023, 641
  • [7] Deep indoor illumination estimation based on spherical gaussian representation with scene prior knowledge
    Xu, Chao
    Han, Cheng
    Yang, Huamin
    Zhang, Chao
    Lu, Shiyu
    JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2024, 36 (10)
  • [8] Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition
    Miao, Bo
    Zhou, Liguang
    Mian, Ajmal Saeed
    Lam, Tin Lun
    Xu, Yangsheng
    2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 2069 - 2075
  • [9] Depression Micro-Expression Recognition Technology Based on Multimodal Knowledge Graphs
    Gu, Shanshan
    Sun, Xinlu
    Chen, Abin
    Tao, Weijing
    TRAITEMENT DU SIGNAL, 2024, 41 (04) : 2047 - 2056
  • [10] A survey on dynamic scene understanding using temporal knowledge graphs: From scene knowledge representation to extrapolation
    Lu, Linnan
    Si, Guannan
    Liang, Xinyu
    Li, Mingshen
    Zhou, Fengyu
    NEUROCOMPUTING, 2025, 635