NUS-PRO: A New Visual Tracking Challenge

NUS-PRO is the abbreviation for 'NUS People and Rigid Objects Dataset', which consists of 365 image sequences with manually labeled bounding boxes and occlusion status. NUS-PRO is designed for evaluating algorithms of object tracking.

Download

To meet the demand for developing deep learning model, all annotations are released!

Reference

@article{nus_pro,
    title={{NUS-PRO: A New Visual Tracking Challenge}},
    author={Li, A and Lin, M and Wu, Y and Yang, MH and Yan, S},
    journal={ IEEE Transactions on Pattern Analysis and Machine Intelligence},
    volume={38},
    number={2},
    pages={335--349},
    year={2016}
}