Fs-DSM: Few-Shot Diagram-Sentence Matching via Cross-Modal Attention Graph Model.
Xin HuLingling ZhangJun LiuQinghua ZhengJianlong ZhouPublished in: IEEE Trans. Image Process. (2021)
Keyphrases
- graph model
- cross modal
- multi modal
- natural language
- image retrieval
- multimedia retrieval
- weighted graph
- bipartite graph
- visual recognition
- feature selection
- video sequences
- language model
- graph structure
- visual features
- visual similarity
- multimedia databases
- video content
- machine learning
- information retrieval
- clustering method
- vector space model
- low level
- domain knowledge
- feature vectors
- high dimensional