VSPW

The VSPW dataset is a large-scale dataset for video scene parsing in the wild, containing 2,806 videos with 480x853 pixel frames and 124 semantic categories.

Data and Resources

Cite this as

J. Miao, Y. Wei, Y. Wu, C. Liang, G. Li, Y. Yang (2024). Dataset: VSPW. https://doi.org/10.57702/itsj3nem

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.2403.02689
Author J. Miao
More Authors
Y. Wei
Y. Wu
C. Liang
G. Li
Y. Yang
Homepage https://arxiv.org/abs/2109.08020