Multimodal Relation Extraction via a Mixture of Hierarchical Visual Context Learners.
Xiyang LiuChunming HuRichong ZhangKai SunSamuel MensahYongyi MaoPublished in: WWW (2024)
Keyphrases
- relation extraction
- visual context
- information extraction
- automatic extraction
- named entities
- semantic relations
- domain specific
- temporal context
- question answering
- named entity recognition
- scene interpretation
- semantic context
- semantic features
- multi modal
- multimedia
- visual scene
- object detection
- audio visual
- co occurrence
- text mining
- relevance feedback
- multiscale
- visual words
- conditional random fields
- text classification
- image classification
- search engine