Referring image segmentation with attention guided cross modal fusion for semantic oriented languages.
Qianli ZhouRong WangHai-Miao HuQuange TanWenjin ZhangPublished in: Frontiers Comput. Sci. (2022)
Keyphrases
- cross modal
- image segmentation
- multi modal
- semantic concepts
- multimedia retrieval
- natural language
- visual similarity
- image processing
- visual recognition
- multiscale
- perceptual information
- image retrieval
- semantic similarity
- multimedia databases
- graph cuts
- computer vision
- image representation
- visual data
- test collection
- low level
- similarity measure
- feature selection