Edit model card


Table of Contents

Model Details

Unicorn accomplishes the great unification of the network architecture and the learning paradigm for four tracking tasks. Unicorn puts forwards new state-of-the-art performance on many challenging tracking benchmarks using the same model parameters. This model has an input size of 800x1280.


Direct Use

This model can be used for:

  • Single Object Tracking (SOT)
  • Multiple Object Tracking (MOT)
  • Video Object Segmentation (VOS)
  • Multi-Object Tracking and Segmentation (MOTS)

This model can simultaneously deal with SOT, MOT17, VOS, and MOTS Challenge

Evaluation Results

MOT17 MOTA (%): 77.2 MOTS sMOTSA (%): 65.3

Citation Information

  title={Towards Grand Unification of Object Tracking},
  author={Yan, Bin and Jiang, Yi and Sun, Peize and Wang, Dong and Yuan, Zehuan and Luo, Ping and Lu, Huchuan},
Downloads last month
Hosted inference API

Inference API has been turned off for this model.