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

页码：15787 / 15788

页数：2

共 50 条

[1] RGB-D Scene Recognition based on Object-Scene Relation and Semantics-Preserving Attention
Guo, Yuhui
Liang, Xun
PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR '21), 2021, : 127 - 134
[2] RGB-D Scene Recognition with Object-to-Object Relation
Song, Xinhang
Chen, Chengpeng
Jiang, Shuqiang
PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, : 600 - 608
[3] Contextual object category recognition for RGB-D scene labeling
Ali, Haider
Shafait, Faisal
Giannakidou, Eirini
Vakali, Athena
Figueroa, Nadia
Varvadoukas, Theodoros
Mavridis, Nikolaos
ROBOTICS AND AUTONOMOUS SYSTEMS, 2014, 62 (02) : 241 - 256
[4] Image Representations With Spatial Object-to-Object Relations for RGB-D Scene Recognition
Song, Xinhang
Jiang, Shuqiang
Wang, Bohan
Chen, Chengpeng
Chen, Gongwei
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 : 525 - 537
[5] Indoor Scene Recognition from RGB-D Images by Learning Scene Bases
Wan, Shaohua
Hu, Changbo
Aggarwal, J. K.
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 3416 - 3421
[6] A method proposal of scene recognition for RGB-D cameras
Danciu, Gabriel-Mihail
2016 IEEE 11TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI), 2016, : 301 - 304
[7] Learning Effective RGB-D Representations for Scene Recognition
Song, Xinhang
Jiang, Shuqiang
Herranz, Luis
Chen, Chengpeng
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (02) : 980 - 993
[8] Motion-Based Object Segmentation Based on Dense RGB-D Scene Flow
Shao, Lin
Shah, Parth
Dwaracherla, Vikranth
Bohg, Jeannette
IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04): : 3797 - 3804
[9] MSN: Modality separation networks for RGB-D scene recognition
Xiong, Zhitong
Yuan, Yuan
Wang, Qi
NEUROCOMPUTING, 2020, 373 : 81 - 89
[10] Translate-to-Recognize Networks for RGB-D Scene Recognition
Du, Dapeng
Wang, Limin
Wang, Huiling
Zhao, Kai
Wu, Gangshan
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 11828 - 11837

← 1 2 3 4 5 →