'What' and 'Where' both matter: dual cross-modal graph convolutional networks for multimodal named entity recognition.
Zhengxuan ZhangJianying ChenXuejie LiuWeixing MaiQianhua CaiPublished in: Int. J. Mach. Learn. Cybern. (2024)
Keyphrases
- cross modal
- named entity recognition
- multi modal
- information extraction
- named entities
- natural language processing
- maximum entropy
- semi supervised
- multimedia retrieval
- text summarization
- conditional random fields
- image retrieval
- visual recognition
- visual data
- multimedia databases
- visual similarity
- wordnet
- text retrieval
- learning algorithm
- image classification
- question answering
- co occurrence
- text mining
- probabilistic model
- pairwise
- multimedia
- artificial intelligence