Generalized Zero-Shot Learning Using Multimodal Variational Auto-Encoder With Semantic Concepts.
Nihar BendreKevin DesaiPeyman NajafiradPublished in: ICIP (2021)
Keyphrases
- semantic concepts
- multi modal
- visual features
- image annotation
- low level
- image search
- image segmentation
- visual content
- image collections
- semantic similarity
- low level features
- semantic concept detection
- semantic information
- multimedia content
- video analysis
- multimedia data
- computer vision
- text documents
- high level
- visual concepts
- multimedia
- image regions
- co occurrence
- multiscale