LAVT: Language-Aware Vision Transformer for Referring Image Segmentation.
Zhao YangJiaqi WangYansong TangKai ChenHengshuang ZhaoPhilip H. S. TorrPublished in: CVPR (2022)
Keyphrases
- image segmentation
- computer vision
- computational vision
- image processing
- graph cuts
- fuzzy logic
- programming language
- language learning
- fault diagnosis
- active contours
- real time
- vision system
- power system
- markov random field
- natural language
- multiscale
- boundary detection
- machine learning
- language processing
- region segmentation
- modeling language
- medical imaging
- deformable models
- energy function
- artificial intelligence
- genetic algorithm
- spectral clustering
- energy minimization
- shape prior
- graph partitioning
- texture segmentation
- level set
- unsupervised image segmentation
- method for image segmentation
- multilevel thresholding
- variational level set