Fine-Grained and Semantic-Guided Visual Attention for Image Captioning.
Zongjian ZhangQiang WuYang WangFang ChenPublished in: WACV (2018)
Keyphrases
- fine grained
- visual attention
- salient regions
- visual perception
- coarse grained
- input image
- saliency map
- multiscale
- image data
- attention mechanism
- eye movements
- eye tracking
- image classification
- image features
- biological vision systems
- visual search
- visual attention model
- image segmentation
- image collections
- stereoscopic images
- image retrieval
- visual scene
- visual saliency detection
- image content
- access control
- region of interest
- saliency detection
- real time
- salient features
- image representation
- low level
- visual input
- data lineage
- key frames
- visual motion
- visual saliency
- affine invariant
- image regions
- denoising
- object recognition
- machine learning