A Short Survey on Deep Learning for Skeleton-based Action Recognition

被引：2

作者：

Wang, Wei ^{[1
]}

Zhang, Yu-Dong ^{[1
]}

机构：

[1] Univ Leicester, Sch Comp & Math Sci, Leicester LE1 7RH, Leics, England

来源：

COMPANION PROCEEDINGS OF THE 14TH IEEE/ACM INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING (UCC'21 COMPANION) | 2021年

基金：

英国医学研究理事会;

关键词：

Recurrent Neural Networks; Convolutional Neural Networks; Graph Convolutional Neural Networks; Action recognition; Skeleton; Deep learning; MOTION;

D O I：

10.1145/3492323.3495571

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Motion recognition is an essential aspect of computer vision used in a wide range of fields and has received much attention as one of the most popular research topics. Traditional motion recognition studies are mainly based on RGB images and videos, but the lighting and viewpoint of RGB data can easily affect the model performance. Skeleton sequences are the most common type of coordinate data and avoid these problems. Therefore, more and more research has been conducted to combine skeleton sequences with deep learning to solve action recognition problems, and awe-inspiring results have been obtained. In particular, the recent rapid emergence of GCN methods, which fit well with the characteristics of skeletal data, offers a promising future for action recognition based on skeletal sequences. In this paper, we first introduce the acquisition of skeletal data and some common datasets, summarise some of the research in the field of skeletal sequence-based action recognition, and briefly discuss the future directions of this kind of research.

引用

页数：6

共 37 条

[1]

Baccouche Moez, 2011, Human Behavior Unterstanding. Proceedings Second International Workshop, HBU 2011, P29, DOI 10.1007/978-3-642-25446-8_4

[2]

Bell T., 1999, Wiley Encyclopedia of Electrical and Electronics Engineering, P1, DOI DOI 10.1002/047134608X.W8298

[3] Measurement accuracy and dependence on external influences of the iPhone X TrueDepth sensor [J].

Breitbarth, Andreas ;

Schardt, Timothy ;

Kind, Cosima ;

Brinkmann, Julia ;

Dittrich, Paul-Gerald ;

Notni, Gunther .

PHOTONICS AND EDUCATION IN MEASUREMENT SCIENCE, 2019, 11144

[4] JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition [J].

Cai, Jinmiao ;

Jiang, Nianjuan ;

Han, Xiaoguang ;

Jia, Kui ;

Lu, Jiangbo .

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, :2734-2743

[5] OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields [J].

Cao, Zhe ;

Hidalgo, Gines ;

Simon, Tomas ;

Wei, Shih-En ;

Sheikh, Yaser .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (01) :172-186

[6]

Cheng GC, 2015, Arxiv, DOI arXiv:1501.05964

[7]

Du Y, 2015, PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, P579, DOI 10.1109/ACPR.2015.7486569

[8]

Du Y, 2015, PROC CVPR IEEE, P1110, DOI 10.1109/CVPR.2015.7298714

[9] Optimized Skeleton-based Action Recognition via Sparsified Graph Regression [J].

Gao, Xiang ;

Hu, Wei ;

Tang, Jiaxiang ;

Liu, Jiaying ;

Guo, Zongming .

PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, :601-610

[10] Structured Time Series Analysis for Human Action Segmentation and Recognition [J].

Gong, Dian ;

Medioni, Gerard ;

Zhao, Xuemei .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (07) :1414-1427

← 1 2 3 4 →