P2T: Pyramid Pooling Transformer for Scene Understanding.
Yu-Huan WuYun LiuXin ZhanMing-Ming ChengPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Keyphrases
- scene understanding
- object detection
- object recognition
- vision system
- scene recognition
- d scene
- spatial pyramid matching
- video surveillance
- robot navigation
- multiscale
- scale space
- scene categorization
- scene labeling
- image representation
- image classification
- scene interpretation
- scene classification
- indoor scenes
- geometric reasoning
- single image
- input image
- image parsing
- machine learning
- background subtraction
- object class
- bag of features
- multi class
- computer vision