Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention.
Honglun ZhangWenqing ChenJidong TianYongkun WangYaohui JinPublished in: CoRR (2018)
Keyphrases
- image data
- image content
- input image
- image retrieval
- visual attention
- multiscale
- image features
- image classification
- visual perception
- image regions
- image representation
- region of interest
- higher level
- multi domain
- keypoints
- low level
- object recognition
- visual attention model
- natural scenes
- real time
- eye tracking
- domain specific
- general purpose
- computer vision