SLViT: Scale-Wise Language-Guided Vision Transformer for Referring Image Segmentation.
Shuyi OuyangHongyi WangShiao XieZiwei NiuRuofeng TongYen-Wei ChenLanfen LinPublished in: IJCAI (2023)
Keyphrases
- image segmentation
- computer vision
- image processing
- computational vision
- multiscale
- programming language
- scale space
- fuzzy logic
- natural language
- vision system
- region growing
- medical imaging
- specification language
- markov random field
- deformable models
- language learning
- boundary detection
- real time
- segmentation algorithm
- graph cuts
- image analysis
- scale invariant
- level set method
- gray level
- language processing
- markov random field model
- sea surface
- object segmentation
- fuzzy c means
- spectral clustering
- fault diagnosis
- segmentation method
- pairwise
- machine learning
- neural network