A Caption Is Worth A Thousand Images: Investigating Image Captions for Multimodal Named Entity Recognition.
Shuguang ChenGustavo AguilarLeonardo NevesThamar SolorioPublished in: CoRR (2020)
Keyphrases
- input image
- image collections
- image data
- named entity recognition
- image features
- test images
- visual features
- image retrieval
- image classification
- web images
- image regions
- image content
- information extraction
- segmentation method
- bounding box
- image database
- segmentation algorithm
- named entities
- natural language processing
- image representation
- image annotation
- visual content
- text summarization
- maximum entropy
- conditional random fields
- low level
- visual concepts
- textual descriptions
- similarity measure
- object recognition
- visual information
- computer vision
- text regions