Cascaded Cross-Modal Transformer for Audio-Textual Classification.

Nicolae-Catalin Ristea Andrei Anghel Radu Tudor Ionescu

Published in: CoRR (2024)

Keyphrases

cross modal
multi modal
multimedia
image retrieval
multimedia retrieval
visual recognition
image classification
machine learning
feature space
feature vectors
text classification
perceptual information
visual similarity
multimedia databases
training set
feature selection
visual information
feature set
high level