Back to search

Article

Boosting Human Pose Estimation via Heatmap Refinement

2024-07-16

Abstract excerpt

Human pose estimation based on heatmap regression has achieved significant success in recent years. However, the semantic ambiguity caused by traditional hand-crafted heatmaps seriously affects the model performance. Specifically, hand-crafted heatmaps generated with a fixed Gaussian kernel are semantically misaligned. Various Gaussian covered areas for keypoints with the same type may cause model learning confusi...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
b0e812f9-5143-5af5-8747-cc5d4c65d95c
DOI
10.22541/au.172114403.33945828/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Boosting Human Pose Estimation via Heatmap RefinementDOI 10.22541/au.172114403.33945828/v1
Select a neighboring publication to make it the new centre.