logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Spatial-temporal attention augmented graph convolution method based on human posture response

delete2025-08-31
delete0
PRE
AI
田磊 cover
田磊 (Lei Tian) *
Z
Zhanhao Yang
J
Jiachen Yang
C
Chengshen Lao
J
Jiahuan Hu
DOI：10.1016/j.sna.2025.117017delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Novel ST-E-GCN architecture enhances spatiotemporal feature learning through channel-wise attention mechanisms. • Real-time pose-responsive lighting control achieves about 100 ms latency in stage performance synchronization. • 4.87 % accuracy improvement on complex dance datasets compared to baseline ST-GCN models. • Hardware-software co-design integrates embedded systems with adaptive DMX512 protocol parsing.

Journal

Sensors and Actuators A-Physical cover
Sensors and Actuators A-Physical
IF:
4.9
Papers:
1.5W
Citations:
3.3W

Organization

No organization information available