Nested-TNT: Hierarchical Vision Transformers with Multi-Scale Feature Processing.
Yuang LiuZhiheng QiuXiaokai QinPublished in: CoRR (2024)
Keyphrases
- multiscale
- real time
- coarse to fine
- hierarchical structure
- computer vision
- data processing
- feature vectors
- vision system
- image processing
- databases
- hierarchical data
- visual processing
- hierarchical clustering
- scale space
- image representation
- information processing
- wavelet transform
- probabilistic model
- feature representation
- optic flow
- feature values
- data model
- similarity measure
- deep structure