Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation

@article{Li2018VideoOS,
  title={Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation},
  author={Xiaoxiao Li and Chen Change Loy},
  journal={CoRR},
  year={2018},
  volume={abs/1803.04242}
}
The problem of semi-supervised video object segmentation, in the context of the 2018 DAVIS Challenge [2], can become extremely challenging when multiple instances coexist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing failures in tracking. In this study, we formulate a deep recurrent network that combines temporal propagation and re-identification functionalities into an end-to-end framework. In particular… CONTINUE READING
3 Citations
32 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Similar Papers

Loading similar papers…