DAVIS Dataset

The DAVIS dataset contains 60 training sequences and 30 validation sequences, with high-quality densely-annotated segmentation mask annotation for each frame.

Data and Resources

Cite this as

Hongbin Xu, Weitao Chen, Feng Xiao, Baigui Sun, Wenxiong Kang (2024). Dataset: DAVIS Dataset. https://doi.org/10.57702/dogxsvtb

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2403.08310
Citation
  • https://doi.org/10.48550/arXiv.1706.09364
  • https://doi.org/10.48550/arXiv.2103.10391
Author Hongbin Xu
More Authors
Weitao Chen
Feng Xiao
Baigui Sun
Wenxiong Kang
Homepage https://www.davis-benchmark.org/