Cross Modal Few-Shot Contextual Transfer for Heterogenous Image Classification.
Zhikui ChenXu ZhangWei HuangJing GaoSuhua ZhangPublished in: Frontiers Neurorobotics (2021)
Keyphrases
- cross modal
- image classification
- visual recognition
- visual features
- visual similarity
- multi modal
- visual data
- bag of words
- video sequences
- semantic concepts
- image representation
- image search
- multimedia retrieval
- image retrieval
- feature extraction
- contextual information
- transfer learning
- key frames
- visual information
- image features
- visual words
- multimedia databases
- visual content
- video data
- multi label
- image annotation
- object detection
- data sources
- perceptual information
- video content
- image understanding
- web images
- bag of features
- scene classification