You're currently viewing an old version of this dataset. To see the current version, click here.

DiDemo

Text-Video Retrieval (TVR) is a pivotal task in the realm of multimodal research, which aims to find the most relevant video content within a repository in response to the text query, and vice versa.

Data and Resources

Cite this as

Meng Cao, Long Chen, Mike Zheng Shou, Can Zhang, Yuexian Zou (2024). Dataset: DiDemo. https://doi.org/10.57702/d8wjkgdy

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Meng Cao
More Authors
Long Chen
Mike Zheng Shou
Can Zhang
Yuexian Zou
Homepage https://github.com/Microsoft/DeepVideo