Auto-encoder-based shared mid-level visual dictionary learning for scene classification using very high resolution remote sensing images.
Gong ChengPeicheng ZhouJunwei HanLei GuoJungong HanPublished in: IET Comput. Vis. (2015)
Keyphrases
- mid level
- scene classification
- sparse coding
- low level
- sparse representation
- image representation
- image classification
- visual words
- low level features
- visual information
- natural scenes
- object recognition
- natural images
- high level
- action recognition
- superpixels
- visual concepts
- bag of words
- image retrieval
- bit rate
- object categories
- visual features
- higher level
- multiscale
- image content
- image features
- feature space
- visual content
- active learning
- maximum likelihood
- high dimensional
- training examples
- saliency map
- computer vision