FASTCC: A lightweight human pose detection method leveraging SimCC

As a focal area within computer vision algorithms, human pose estimation algorithms find applications in diverse fields such as security and virtual reality. Achieving a balance between speed and accuracy is imperative for practical applications. Existing methods often present a trade-off between high accuracy and real-time performance. In response, this paper introduces the Fast Coordinate Classification (FastCC) detection head. It employs a shared fully connected Transformer for global self-attention operations on feature layers from the backbone network. The spatial attention coordinate encoder then outputs the coordinates of the horizontal and vertical axes of the keypoints, which are subsequently combined to derive the actual keypoint positions. Experimental evaluations conducted on the COCO and MPII datasets demonstrate that our detection head enhances the accuracy of human pose estimation algorithms while maintaining a lightweight design, outperforming the traditional heatmap method.