Visual-Semantic Transformer for Scene Text Recognition.
Xin TangYongquan LaiYing LiuYuanyuan FuRui FangPublished in: CoRR (2021)
Keyphrases
- scene text recognition
- visual information
- semantic knowledge
- semantic content
- high level
- object recognition
- semantic information
- natural language
- semantically relevant
- semantic context
- high level semantics
- semantic web
- visual features
- semantic space
- visual concepts
- semantic features
- context dependent
- computer vision
- domain ontology
- fault diagnosis
- low level
- power system
- fuzzy logic
- image classification
- domain knowledge
- semantically equivalent
- semantic labels
- co occurrence
- visual similarity
- data sets
- semantic search
- visual perception
- semantic analysis
- visual data