Optimizing rgb-d semantic segmentation through multi-modal interaction and pooling attention.
Shuai ZhangMinghong XiePublished in: CoRR (2023)
Keyphrases
- multi modal
- semantic segmentation
- superpixels
- conditional random fields
- weakly supervised
- object categories
- object segmentation
- scene classification
- pascal voc
- high dimensional
- image understanding
- image annotation
- object class
- high level
- image representation
- object detection
- image set
- computer vision
- object classes
- long range
- humanoid robot
- multiscale