PECC: Position Encoding Coordinate Classification System Design for Human Pose Estimation

Tao Zhang

doi:10.1109/TSMC.2025.3649204

PECC: Position Encoding Coordinate Classification System Design for Human Pose Estimation

2026-01-14

0

PRE

AI

DOI：10.1109/TSMC.2025.3649204

Original

Original request for help

Save

Abstract

En 中文

Coordinate classification is an efficient approach to 2-D human pose estimation (HPE), treating keypoint predictions as sub-pixel bins along horizontal and vertical axes, thereby avoiding the computationally intensive upsampling process required in traditional heatmap-based methods. In this article, we introduce the Position Encoding Coordinate Classification (PECC) system, which enhances coordinate classification by embedding position information directly into keypoint feature representations through a novel position encoding mechanism. We further design a tailored attention mechanism, Filtering Amplified Attention (FAA), optimized for coordinate classification. FAA provides finer relative positional information, improving the system’s ability to model relationships between keypoints and enhancing coordinate localization accuracy. Our method maintains the efficiency of coordinate classification by utilizing 1-D vectors, significantly reducing model parameters and computational cost. Additionally, the incorporation of positional encoding enhances the system’s ability to effectively model and exploit spatial information within a coordinate-classification-based pose estimation framework. Extensive experiments on mainstream datasets demonstrate that PECC achieves superior accuracy and robustness in 2-D HPE, advancing the state-of-the-art in this domain.

Keywords:

Computer vision

coordinate classification system

deep learning

human pose estimation (HPE)

position encoding

PECC: Position Encoding Coordinate Classification System Design for Human Pose Estimation

Abstract

Journal

Organization