AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings.
Pratik MazumderPravendra SinghKranti Kumar ParidaVinay P. NamboodiriPublished in: WACV (2021)
Keyphrases
- multi modal
- audio visual
- person authentication
- audio features
- high dimensional
- low level
- multi modality
- feature set
- feature space
- image features
- feature extraction
- feature vectors
- multi stream
- image search
- audio visual speech recognition
- computer vision
- video search
- image annotation
- visual information
- co occurrence
- high level