.png){kind=icon}
.png){kind=icon}
Return
Spatiotemporal correlation based self-adaptive pose estimation in complex scenes
.png){kind=icon}
OA
AI
DOI：10.1016/j.dcan.2024.03.007.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A character redetection model is proposed to dynamically adjust the foreground extraction strategy. • The reliability of multi-feature collaborative judgment is based on spatiotemporal correlation. • An uncertainty graph structure is designed to model the various poses of the characters. • The topology of graphs is adaptively learned in an end-to-end manner. • The proposed method improves the robustness and accuracy of pose estimation.
Keywords:
Large-scale AI models
Pose estimation
Graph convolutional network
Computer vision
Character redetection
Graph structure
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
406
Citations:
3.5K
View more organizations