Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images.
Fahimeh FooladgarShohreh KasaeiPublished in: CoRR (2019)
Keyphrases
- multi modal
- depth images
- color information
- superpixels
- depth information
- depth map
- pose estimation
- low resolution
- image annotation
- color images
- color space
- multiscale
- high dimensional
- image sequences
- natural images
- object categories
- input image
- support vector machine
- machine learning
- segmentation method
- conditional random fields
- viewpoint