Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization.
Wenjin HuLang QiaoWendong KangXinyue ShiPublished in: J. Imaging (2023)
Keyphrases
- image features
- image analysis
- input image
- image data
- multiscale
- semantic concepts
- image collections
- low level
- image content
- image representation
- image classification
- computer vision
- multi modal
- low level visual features
- visual features
- image retrieval
- image database
- semantic gap
- keypoints
- image regions
- image segmentation
- feature set
- image matching
- low level features
- object recognition
- knowledge base