DEFEATnet - A Deep Conventional Image Representation for Image Classification.
Shenghua GaoLixin DuanIvor W. TsangPublished in: IEEE Trans. Circuits Syst. Video Technol. (2016)
Keyphrases
- image representation
- image classification
- bag of words
- image content
- image features
- visual words
- visual features
- feature representations
- visual recognition
- quadtree
- multiscale
- scene classification
- representation scheme
- sparse coding
- feature extraction
- scene recognition
- object recognition
- receptive fields
- bag of features
- low level features
- bag of visual words
- spatial pyramid
- pattern representation
- sparse representation
- feature space
- compressive sensing
- visual content
- region segmentation
- computer vision
- image classification and retrieval