MSR Video to Text (MSR-VTT)

The MSR-VTT dataset is a large-scale video captioning benchmark that contains 10,000 video clips with 200,000 descriptions.

Data and Resources

Cite this as

Yuyu Guo, Jingqiu Zhang, Lianli Gao (2024). Dataset: MSR Video to Text (MSR-VTT). https://doi.org/10.57702/guwcoesk

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yuyu Guo
More Authors
Jingqiu Zhang
Lianli Gao
Homepage https://ai.stanford.edu/~aishwarya/video-captioning/datasets/msr-vtt.html