Mutatt: Visual-Textual Mutual Guidance For Referring Expression Comprehension.
Shuai WangFan LyuWei FengSong WangPublished in: ICME (2020)
Keyphrases
- visual representations
- visual features
- visual information
- metadata
- high level
- low level
- visual perception
- natural language
- object recognition
- neural network
- visual representation
- multi modal
- textual features
- visual exploration
- concept mapping
- visual appearance
- user generated
- keywords
- case study
- multimedia
- learning algorithm