Reproduce “ProAlign: Progressive Positional and Prototype-Guided Alignment for Aerial-Ground Person Re-Identification” 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

Qiao Li, Jing Chen, Cong Wu, Kun He, Ruiying Du, Lei Tan

ProAlign addresses cross-view person re-identification between aerial and ground cameras. It calibrates patch positions through transformer layers and aligns view-specific identity prototypes during training. On CARGO’s ALL protocol, it achieves 68.27% Rank-1 and 62.47% mAP, above the strongest comparator on each metric. Its advantage is not uniform: GSAlign leads on CARGO A-to-G Rank-1 and mAP.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.