About GMOT-40(Jì Mò-40)


GMOT-40 is the first public dense dataset for Generic Multiple Object Tracking (GMOT). It contains 40 carefully annotated sequences evenly distributed among 10 object categories. Beyond the data, a challenging protocal, one-shot GMOT, is adopted and a series of baseline algorithms is introduced. GMOT-40 is featured in

  • Dense objects. Over 80 objects of the same class could appear in one frame.
  • High-quality label. Manual annotation with careful inspection in each frame.
  • Diversity in target. Large variability between classes and within the sequences of the same class.
  • Real world challenges. Occlusion, target enter/exiting, motion blur, deformation and so on.
  • Challenging protocol. One-shot GMOT protocol is adopted for evaluation.
  • New baselines. A series of baseline methods for one-shot GMOT task is introduced.

Please check out the benchmark details and download links at Download page, baseline results at Leaderboard page.

News


  • 2021-07: Trajectory labels are available. All data of GMOT-40 is released now!
  • 2021-04: Image sequences and one-shot detection results are available!
  • 2021-03: The official website is launched now!
  • 2021-03: GMOT-40 paper is accepted to CVPR 2021!

Reference


Please consider citing GMOT-40 if it is helpful for you :)

GMOT-40: A Benchmark for Generic Multiple Object Tracking
H. Bai*, W. Cheng*, P. Chu*, K. Zhang, and H. Ling
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Contact


We appreciate questions and suggestions to Wensheng Cheng(general things) at wenscheng@cs.stonybrook.edu or Haibin Ling(commercial use) at hling@cs.stonybrook.edu.