SP-ViT: Learning 2D Spatial Priors for Vision Transformers.
Yuxuan ZhouWangmeng XiangChao LiBiao WangXihan WeiLei ZhangMargret KeuperXian-Sheng HuaPublished in: BMVC (2022)
Keyphrases
- learning process
- learning mechanism
- spatio temporal
- online learning
- learning systems
- real time
- learning algorithm
- prior knowledge
- learning problems
- image processing
- incremental learning
- supervised learning
- human vision
- inductive inference
- learning community
- spatial data
- background knowledge
- expert systems
- video sequences
- training data
- computer vision
- data sets