Login / Signup
Codec at SemEval-2022 Task 5: Multi-Modal Multi-Transformer Misogynous Meme Classification Framework.
Ahmed Mahran
Carlo Alessandro Borella
Konstantinos Perifanos
Published in:
SemEval@NAACL (2022)
Keyphrases
</>
multi modal
cross modal
multi modality
text classification
machine learning
feature extraction
high dimensional
feature vectors
classification accuracy
image classification
image annotation
semantic concepts
single modality
feature space
audio visual