Reproduce “PTB-TIR: A Thermal Infrared Pedestrian Tracking Benchmark” 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 Liu, Zhenyu He, Xin Li, Yuan Zheng

The authors introduce PTB-TIR, a benchmark and toolkit for short-term thermal-infrared pedestrian tracking. It contains 60 manually annotated sequences and 30,128 frames, with nine challenge labels, for comparing trackers and selected components. In a controlled ridge-regression test, HOG features achieve success-curve AUC 0.59 versus 0.23 for grayscale pixels; these are paper-reported results for that baseline, not corrected annotations.

Summary by alphaXiv.

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