Skip to main navigation Skip to search Skip to main content

Skeleton-Based Online Action Detection with Temporal Enhancement

  • Boyu Ying
  • , Junyuan Xiang
  • , Wei Zheng
  • , Zhiyong Wang
  • , Weihong Ren
  • , Shuli Luo*
  • , Honghai Liu*
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen
  • New York University
  • Shenzhen Children's Hospital

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

Abstract

Online action detection focuses on recognizing actions happening in the latest frames of streaming video. Given the strong correlation between human skeletons and actions, many researchers have attempted to use skeletons for online action detection. Recently, spatio-temporal graph convolutional methods achieve good action modeling effects, but they have limited capability for detecting actions in the latest frames. In this paper, we introduce a temporal enhancement technique to optimize the performance of skeleton-based online action detection, involving a temporal feature enhancement module and a motion difference module. The temporal feature enhancement module, modified based on Transformer, enhances the latest features temporally. The motion difference module introduces motion features into the network. Experimental results demonstrate that our method is competitive.

Original languageEnglish
Title of host publicationEmotional Intelligence - Second CSIG Conference, CEI 2024, Proceedings
EditorsXiaohua Huang, Qirong Mao
PublisherSpringer Science and Business Media Deutschland GmbH
Pages145-156
Number of pages12
ISBN (Print)9789819650835
DOIs
StatePublished - 2025
Externally publishedYes
Event2nd CSIG Conference on Emotional Intelligence, CEI 2024 - Nanjing, China
Duration: 6 Dec 20248 Dec 2024

Publication series

NameCommunications in Computer and Information Science
Volume2450 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference2nd CSIG Conference on Emotional Intelligence, CEI 2024
Country/TerritoryChina
CityNanjing
Period6/12/248/12/24

Keywords

  • Online action detection
  • Skeleton-based
  • Temporal action modeling

Fingerprint

Dive into the research topics of 'Skeleton-Based Online Action Detection with Temporal Enhancement'. Together they form a unique fingerprint.

Cite this