AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings.
Pratik MazumderPravendra SinghKranti Kumar ParidaVinay P. NamboodiriPublished in: CoRR (2020)
Keyphrases
- multi modal
- audio visual
- person authentication
- audio features
- multi modality
- multi stream
- audio visual speech recognition
- image features
- feature set
- high dimensional
- single modality
- cross modal
- feature vectors
- feature extraction
- video search
- spatial information
- medical images
- dimensionality reduction
- co occurrence
- low level
- uni modal