G-Ref

G-Ref is a dataset for referring image segmentation, comprising 104K referring language expressions for around 55K objects in about 27K images.

Data and Resources

Cite this as

Zicheng Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, Wei Ke (2024). Dataset: G-Ref. https://doi.org/10.57702/dm287wk3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2307.00997
Citation
  • https://doi.org/10.48550/arXiv.2212.01769
Author Zicheng Zhang
More Authors
Yi Zhu
Jianzhuang Liu
Xiaodan Liang
Wei Ke
Homepage https://ai.stanford.edu/~jgao/papers/G-Ref.pdf