Text-Image Scene Graph Fusion for Multimodal Named Entity Recognition.
Jian ChengKaifang LongShuang ZhangTian ZhangLianbo MaShi ChengYinan GuoPublished in: IEEE Trans. Artif. Intell. (2024)
Keyphrases
- named entity recognition
- input image
- single image
- text summarization
- image regions
- information extraction
- named entities
- image features
- image classification
- natural language processing
- image representation
- image content
- segmentation method
- low level
- visual data
- image retrieval
- fusion method
- conditional random fields
- named entity recognizer
- information retrieval
- named entity disambiguation
- segmentation algorithm
- semi supervised
- similarity measure
- artificial intelligence
- graphical models
- text mining
- relevance feedback
- maximum entropy
- knowledge representation
- data analysis
- proper names
- image segmentation