YNAO OpenIR  > 天文技术实验室
Identifying players in broadcast videos using graph convolutional network
Feng Tao1; Ji KF(季凯帆)2; Bian Ang1; Liu Chang3; Zhang Jianzhou1
Source PublicationPattern Recognition
2022-04
Volume124
DOI10.1016/j.patcog.2021.108503
Contribution Rank第2完成单位
Indexed BySCI ; EI
KeywordGraph representation learning Graph embedding Pre-trained model Player identification
Abstract

The person representation problem is a critical bottleneck in the player identification task. However, the current approaches for player identification utilizing the entire image features only are not sufficient to preserve identities due to the reliance on visible visual representations. In this paper, we propose a novel player representation method using a graph-powered pose representation to resolve this bottleneck problem. Our framework consists of three modules: (i.) a novel pose-guided representation module that is able to capture the pose changes dynamically and their associated effects; (ii.) a pose-guided graph embedding module using both the image deep features and the pose structure information for a better player representation inference; (iii.) an identification module as a player classifier. Experiment results on the real-world sport game scenarios demonstrate that our method achieves state-of-the-art identification performance, together with a better player representation.

Funding ProjectN/A
Funding OrganizationN/A
Language英语
Subject Area计算机科学技术 ; 人工智能 ; 模式识别 ; 计算机应用
MOST Discipline Catalogue工学 ; 工学::计算机科学与技术(可授工学、理学学位)
SubtypeArticle
PublisherELSEVIER SCI LTD
Publication PlaceTHE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND
ISSN0031-3203
URL查看原文
WOS IDWOS:000740181700002
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS KeywordNEURAL-NETWORK
EI Accession Number20215311410246
EI KeywordsComputer vision
EI Classification Number723.4 Artificial Intelligence - 723.5 Computer Applications - 741.2 Vision
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ynao.ac.cn/handle/114a53/24753
Collection天文技术实验室
Corresponding AuthorBian Ang
Affiliation1.College of Computer Science, Sichuan University, Chengdu, China
2.Yunnan Observatory, Chinese Academy of Sciences, Kunming, China
3.School of Biological Science and Medical Engineering, Beihang University, Beijing, China
Recommended Citation
GB/T 7714
Feng Tao,Ji KF,Bian Ang,et al. Identifying players in broadcast videos using graph convolutional network[J]. Pattern Recognition,2022,124.
APA Feng Tao,Ji KF,Bian Ang,Liu Chang,&Zhang Jianzhou.(2022).Identifying players in broadcast videos using graph convolutional network.Pattern Recognition,124.
MLA Feng Tao,et al."Identifying players in broadcast videos using graph convolutional network".Pattern Recognition 124(2022).
Files in This Item:
File Name/Size DocType Version Access License
Identifying players (3998KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Feng Tao]'s Articles
[Ji KF(季凯帆)]'s Articles
[Bian Ang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Feng Tao]'s Articles
[Ji KF(季凯帆)]'s Articles
[Bian Ang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Feng Tao]'s Articles
[Ji KF(季凯帆)]'s Articles
[Bian Ang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Identifying players in broadcast videos using graph convolutional network.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.