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
  • [31] Robust and efficient cpu-based rgb-d scene reconstruction
    Li J.
    Gao W.
    Li H.
    Tang F.
    Wu Y.
    Gao, Wei (wgao@nlpr.ia.ac.cn), 2018, MDPI AG (18):
  • [32] Robust and Efficient CPU-Based RGB-D Scene Reconstruction
    Li, Jianwei
    Gao, Wei
    Li, Heping
    Tang, Fulin
    Wu, Yihong
    SENSORS, 2018, 18 (11)
  • [33] Completed Dense Scene Flow in RGB-D Space
    Wang, Yucheng
    Zhang, Jian
    Liu, Zicheng
    Wu, Qiang
    Chou, Philip
    Zhang, Zhengyou
    Jia, Yunde
    COMPUTER VISION - ACCV 2014 WORKSHOPS, PT I, 2015, 9008 : 191 - 205
  • [34] RGB-D Scene Segmentation with Conditional Random Field
    Nasab, Sara Ershadi
    Kasaei, Shohreh
    Sanaei, Esmaeil
    2014 6TH CONFERENCE ON INFORMATION AND KNOWLEDGE TECHNOLOGY (IKT), 2014, : 134 - 139
  • [35] SketchyDepth: from Scene Sketches to RGB-D Images
    Berardi, Gianluca
    Salti, Samuele
    Di Stefano, Luigi
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021), 2021, : 2414 - 2423
  • [36] Intrinsic Scene Decomposition from RGB-D images
    Hachama, Mohammed
    Ghanem, Bernard
    Wonka, Peter
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 810 - 818
  • [37] Radiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images
    Lombardi, Stephen
    Nishino, Ko
    PROCEEDINGS OF 2016 FOURTH INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2016, : 305 - 313
  • [38] When CNNs meet random RNNs: Towards multi-level analysis for RGB-D object and scene recognition
    Caglayan, Ali
    Imamoglu, Nevrez
    Can, Ahmet Burak
    Nakamura, Ryosuke
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2022, 217
  • [39] RGB-D Object Modelling for Object Recognition and Tracking
    Prankl, Johann
    Aldoma, Aitor
    Svejda, Alexander
    Vincze, Markus
    2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 96 - 103
  • [40] 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
12345