Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection

Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities.

Data and Resources

Cite this as

Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque (2024). Dataset: Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection. https://doi.org/10.57702/jsvffyhm

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.2402.09738
Author Eftekhar Hossain
More Authors
Omar Sharif
Mohammed Moshiul Hoque
Homepage https://github.com/eftekhar-hossain/Bengali-Hateful-Memes