StructCap: Structured Semantic Embedding for Image Captioning.
Fuhai ChenRongrong JiJinsong SuYongjian WuYunsheng WuPublished in: ACM Multimedia (2017)
Keyphrases
- image data
- single image
- input image
- image content
- template matching
- test images
- image features
- image retrieval
- semantically meaningful
- image segmentation
- region of interest
- low level
- image analysis
- multiscale
- edge detection
- segmentation method
- image regions
- natural language
- image classification
- high resolution
- image pixels
- image representation
- semantic information
- spatial information
- visual concepts
- watermarking technique