Visual-Semantic Transformer for Scene Text Recognition.
Liang DiaoXin TangJun WangRui FangGuotong XieWeifu ChenPublished in: BMVC (2022)
Keyphrases
- scene text recognition
- semantic content
- object recognition
- low level
- visual information
- high level
- visual features
- higher level
- semantic information
- high level semantics
- visual perception
- natural language
- fuzzy logic
- low level features
- web images
- visual concepts
- semantic concepts
- semantic web
- semantic analysis
- semantic similarity
- semantic annotation
- image retrieval
- wordnet
- semantic search
- video sequences
- semantically meaningful
- visual similarity
- semantic labels
- semantic context
- semantically relevant
- computer vision