A Visual Embedding for the Supervised Image based on self-attention.
Kouwu WangZuwen ChenJie HuangXin LuoPublished in: CACML (2024)
Keyphrases
- selective attention
- visual information
- visual features
- semi supervised
- computer vision
- low level
- unsupervised learning
- vector space
- supervised learning
- visual saliency
- focus of attention
- visual processing
- visual attention
- feature selection
- visual input
- visual field
- machine learning
- multidimensional scaling
- visual representation
- visual cues
- video sequences
- multiscale
- learning algorithm