Benchmark dataset of memes with text transcriptions for automatic detection of multi-modal misogynistic content.
Francesca GaspariniGiulia RizziAurora SaibeneElisabetta FersiniPublished in: CoRR (2021)
Keyphrases
- multi modal
- automatic detection
- benchmark datasets
- multiple modalities
- video search
- multi modality
- semantic information
- image annotation
- automatically detecting
- cross modal
- audio visual
- high dimensional
- multimedia documents
- spoken documents
- semantic concepts
- text retrieval
- multimedia
- broadcast news
- uni modal
- information retrieval
- web images
- information theoretic
- metadata