Reproduce “DPAGait: Dynamic Pose-Knowledge-Aware Network for Robust Gait Recognition in the Wild” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zenan Lin, Junduan Huang, Kun Liu, M. Saad Shakeel, Wenxiong Kang
The authors introduce DPAGait, a gait-recognition system that enriches silhouette inputs with joint, limb, and short-term motion structure while preserving their contours, then combines them with compact SMPL pose features. DPPS improves DeepGaitV2 Rank-1 on Gait3D from 74.4% to 81.1%. Adding the SMPL branch raises SUSTech1K Rank-1 from 81.3% to 85.6%; full-system evaluation covers three datasets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.