Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model.
Shishi XiaoSuizi HuangYue LinYilin YeWei ZengPublished in: CoRR (2023)
Keyphrases
- generative model
- semantic context
- input image
- probabilistic model
- multiscale
- image features
- image content
- image segmentation
- web images
- keywords
- prior knowledge
- em algorithm
- visual features
- pixel level
- image structure
- image regions
- image representation
- image classification
- low level
- image retrieval
- similarity measure
- expectation maximization
- keypoints
- spatial information
- text mining
- image collections
- object categories
- semi supervised
- video annotation
- text information
- visual vocabulary
- information retrieval