Boosting convolutional image captioning with semantic content and visual relationship.
Cong BaiAnqi ZhengYuan HuangXiang PanNan ChenPublished in: Displays (2021)
Keyphrases
- semantic content
- image content
- web images
- image data
- image features
- image retrieval
- visual features
- semantic gap
- image classification
- low level
- visual content
- image representation
- image collections
- low level descriptors
- multiscale
- image search
- visual concepts
- image regions
- visual data
- keypoints
- visual information
- semantic information
- keywords
- spatial information
- machine learning
- video retrieval
- image database
- active learning
- image segmentation
- feature selection
- search engine
- learning algorithm
- image matching
- low level features
- semantic similarity
- natural language processing