Cap2Seg: Inferring Semantic and Spatial Context from Captions for Zero-Shot Image Segmentation.
Guiyu TianShuai WangJie FengLi ZhouYadong MuPublished in: ACM Multimedia (2020)
Keyphrases
- spatial context
- image segmentation
- temporal context
- contextual information
- spatial and temporal
- semantic features
- spatial relationships
- semantic information
- multiscale
- computer vision
- spatial information
- image regions
- segmentation method
- graph cuts
- video content
- image processing
- context aware
- level set
- markov random field
- multi dimensional
- text mining
- high level
- machine learning