Event Detection in Soccer Video Based on Self-Attention

Sifan Ma, En Shao, Xiang Xie*, Wei Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

Abstract

Sports big data technology has become an important technological means of modern sports competition. This paper realizes a novel soccer video event detection algorithm based on self-attention. It extracts key frames through self-attention mechanism, and then obtains the characteristics of time window level through NetVLAD network. Finally, each video clip is classified into 4 types of events (goals, red/yellow card, substitutions and others). The experimental results show that with the introduction of the self-attention mechanism, the classification accuracy on the SoccerNet data set has improved from 67.2% to 74.3%.

Original languageEnglish
Title of host publication2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1852-1856
Number of pages5
ISBN (Electronic)9781728186351
DOIs
Publication statusPublished - 11 Dec 2020
Event6th IEEE International Conference on Computer and Communications, ICCC 2020 - Chengdu, China
Duration: 11 Dec 202014 Dec 2020

Publication series

Name2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020

Conference

Conference6th IEEE International Conference on Computer and Communications, ICCC 2020
Country/TerritoryChina
CityChengdu
Period11/12/2014/12/20

Keywords

  • NetVLAD
  • event detection
  • key frame extraction
  • self-attention

Fingerprint

Dive into the research topics of 'Event Detection in Soccer Video Based on Self-Attention'. Together they form a unique fingerprint.

Cite this