RGB-D Scene Recognition based on Object-Scene Relation

被引：0
作者：
Guo, Yuhui [1 ]
Liang, Xun [1 ]
机构：
[1] Renmin Univ China, 59 Zhongguancun Rd, Beijing RENMIN UNIV, Peoples R China
来源：
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2021年 / 35卷
基金：
中国国家自然科学基金;
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We develop a RGB-D scene recognition model based on object-scene relation(RSBR). First learning a Semantic Network in the semantic domain that classifies the label of a scene on the basis of the labels of all object types. Then, we design an Appearance Network in the appearance domain that recognizes the scene according to local captions. We enforce the Semantic Network to guide the Appearance Network in the learning procedure. Based on the proposed RSBR model, we obtain the state-of-the-art results of RGB-D scene recognition on SUN RGB-D and NYUD2 datasets.
引用
收藏
页码：15787 / 15788
页数：2
相关论文
共 50 条
  • [41] Anisotropic Convolutional Neural Networks for RGB-D Based Semantic Scene Completion
    Li, Jie
    Wang, Peng
    Han, Kai
    Liu, Yu
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (11) : 8125 - 8138
  • [42] A 3D Reconstruction System for Large Scene Based on RGB-D Image
    Wang, Hongren
    Wang, Pengbo
    Wang, Xiaodi
    Peng, Tianchen
    Zhang, Baochang
    INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, 2018, 11266 : 518 - 527
  • [43] RGB-D SCENE CLASSIFICATION VIA HETEROGENEOUS MODEL FUSION
    Liu, Xinda
    Wang, Xueming
    Jiang, Shuqiang
    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 499 - 503
  • [44] RGB-D Scene Image Fusion Algorithm Based on Sparse Atom Fusion
    Liu Fan
    Liu Pengyuan
    Zhang Junning
    Xu Binbin
    ACTA OPTICA SINICA, 2018, 38 (01)
  • [45] Subset based deep learning for RGB-D object recognition
    Bai, Jing
    Wu, Yan
    Zhang, Junming
    Chen, Fuqiang
    NEUROCOMPUTING, 2015, 165 : 280 - 292
  • [46] Point-Based Object Recognition in RGB-D Images
    Wilkowski, Artur
    Kornuta, Tomasz
    Kasprzak, Wlodzimierz
    INTELLIGENT SYSTEMS'2014, VOL 2: TOOLS, ARCHITECTURES, SYSTEMS, APPLICATIONS, 2015, 323 : 593 - 604
  • [47] Combining Features For RGB-D object Recognition
    Khan, Wasif
    Phaisangittisagul, Ekachai
    Ali, Luqman
    Gansawat, Duangrat
    Kumazawa, Itsuo
    2017 INTERNATIONAL ELECTRICAL ENGINEERING CONGRESS (IEECON), 2017,
  • [48] RGB-D Scene Labeling with Multimodal Recurrent Neural Networks
    Fan, Heng
    Mei, Xue
    Prokhorov, Danil
    Ling, Haibin
    2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 203 - 211
  • [49] The roles of scene priming and location p ming in object-scene consistency effects
    Heise, Nils
    Ansorge, Ulrich
    FRONTIERS IN PSYCHOLOGY, 2014, 5
  • [50] Three-dimentional reconstruction of semantic scene based on RGB-D map
    Lin J.-H.
    Wang Y.-J.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2018, 26 (05): : 1231 - 1241
12345