Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts.
Nihar BendreKevin DesaiPeyman NajafiradPublished in: CoRR (2021)
Keyphrases
- semantic concepts
- multi modal
- visual features
- image collections
- semantic similarity
- image search
- low level
- image annotation
- visual content
- low level features
- semantic concept detection
- video analysis
- semantic information
- visual concepts
- multimedia data
- multimedia content
- image processing
- multimedia
- image segmentation
- image understanding
- markov random field
- high dimensional
- knowledge base
- multiscale
- video sequences
- wordnet
- image classification
- key frames
- text documents
- machine learning
- text categorization