Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach

arXiv:2307.01004v2 Announce Type: replace-cross
Abstract: We introduce a novel one-stage end-to-end multi-person 2D pose estimation algorithm, known as Joint Coordinate Regression and Association (JCRA), that produces human pose joints and associations without requiring any post-processing. The proposed algorithm is fast, accurate, effective, and simple. The one-stage end-to-end network architecture significantly improves the inference speed of JCRA. Meanwhile, we devised a symmetric network structure for both the encoder and decoder, which ensures high accuracy in identifying keypoints. It follows an architecture …

abstract algorithm arxiv association cs.cv cs.lg human network neural network novel person post-processing processing regression simple stage type