MSRVTT-QA

Video question answering (VideoQA) requires systems to understand the visual information and infer an answer for a natural language question from it.

Data and Resources

Cite this as

Zenan Xu, Wanjun Zhong, Qinliang Su, Zijing Ou, Fuwei Zhang (2024). Dataset: MSRVTT-QA. https://doi.org/10.57702/1gghtev5

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2404.11865
Citation
  • https://doi.org/10.48550/arXiv.2312.08870
  • https://doi.org/10.48550/arXiv.2307.12058
  • https://doi.org/10.48550/arXiv.2302.02136
  • https://doi.org/10.48550/arXiv.2205.06530
Author Zenan Xu
More Authors
Wanjun Zhong
Qinliang Su
Zijing Ou
Fuwei Zhang
Homepage https://www.ijcai.org/Proceedings/2017/Proceedings/ICAI-2017-106.pdf