Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA

This paper proposes a video question answering model that effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions.

Data and Resources

Cite this as

Hyounghun Kim, Zineng Tang, Mohit Bansal (2024). Dataset: Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA. https://doi.org/10.57702/vzyk3wds

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.2005.06409
Author Hyounghun Kim
More Authors
Zineng Tang
Mohit Bansal
Homepage https://github.com/hyounghk/VideoQADenseCapFrameGate-ACL2020