Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

@article{He2018TrackingBA,
  title={Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers},
  author={Zhen He and Jian Li and Daxue Liu and Hangen He and David Barber},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.03137}
}
Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with popular machine learning approaches which largely reduce the human effort to tune algorithm parameters. However, the commonly used supervised learning approaches require the labeled data (e.g., bounding boxes), which is expensive for videos. Also, the TBD… CONTINUE READING
3
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 73 REFERENCES

Multi-target Tracking in Multiple Non-overlapping Cameras Using Fast-Constrained Dominant Sets

Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati, Marcello Pelillo, Mubarak Shah
  • International Journal of Computer Vision
  • 2017
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Non-Markovian Globally Consistent Multi-object Tracking

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL