Cross-modal transformer with language query for referring image segmentation.
Wenjing ZhangQuange TanPengxin LiQi ZhangRong WangPublished in: Neurocomputing (2023)
Keyphrases
- cross modal
- image segmentation
- multimedia retrieval
- multi modal
- query processing
- database
- natural language
- user queries
- data structure
- visual data
- multiscale
- multimedia information retrieval
- relevance feedback
- markov random field
- query expansion
- multimedia databases
- multimedia
- visual recognition
- indexing techniques
- image understanding
- graph cuts
- retrieval model
- retrieval systems
- visual features
- image data
- data sources
- image retrieval