.png){kind=icon}
.png){kind=icon}
Return
Low-resolution human pose estimation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2022.108579.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating existing methods and reveal that the most dominant heatmap-based methods would suffer more severe model performance degradation from low-resolution, and offset learning is an effective strategy. Established on this observation, in this work we propose a novel Confidence-Aware Learning (CAL) method which further addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Specifically, CAL selectively weighs the learning of heatmap and offset with respect to ground-truth and most confident prediction, whilst capturing the statistical importance of model output in mini-batch learning manner. Extensive experiments conducted on the COCO benchmark show that our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation. (c) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Human pose estimation
Low resolution image
Heatmap learning
Offset learning
Quantization error
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W