Microsoft Research Video Description Corpus (MSVD)

The MSVD dataset is a collection of 1970 open domain clips from YouTube, annotated with variable-length captions.

Data and Resources

Cite this as

Alvaro Peris, Marc Bola˜nos, Petia Radeva, Francisco Casacuberta (2025). Dataset: Microsoft Research Video Description Corpus (MSVD). https://doi.org/10.57702/zwcosfzm

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.1604.03390
Author Alvaro Peris
More Authors
Marc Bola˜nos
Petia Radeva
Francisco Casacuberta
Homepage https://www.microsoft.com/en-us/research/project/microsoft-research-video-description-corpus-msvd/