Clothes image caption generation with attribute detection and visual attention model.
Xianrui LiZhiling YeZhao ZhangMingbo ZhaoPublished in: Pattern Recognit. Lett. (2021)
Keyphrases
- visual attention model
- input image
- image data
- image features
- bounding box
- multiscale
- image representation
- image content
- image retrieval
- high resolution
- biologically inspired
- image structure
- visual attention
- image segmentation
- caption text
- salient regions
- saliency detection
- visual features
- video retrieval
- real time
- image classification
- object detection
- computer vision