Encoder-decoder with double spatial pyramid for semantic segmentation.
Huifang KongJie HuLei FanXiaoxue ZhangYao FangPublished in: J. Electronic Imaging (2019)
Keyphrases
- superpixels
- object class
- scene classification
- visual words
- motion estimation
- image representation
- image classification
- multiscale
- natural images
- object recognition
- object detection
- object segmentation
- conditional random fields
- segmentation method
- bag of words
- segmentation algorithm
- learning algorithm
- object categories
- co occurrence
- object classification
- bag of features
- spatial information
- multiple images
- information extraction
- viewpoint
- feature extraction