BridgeTower: Building Bridges between Encoders in Vision-Language Representation Learning.
Xiao XuChenfei WuShachar RosenmanVasudev LalWanxiang CheNan DuanPublished in: AAAI (2023)
Keyphrases
- learning algorithm
- real time
- learning process
- reinforcement learning
- online learning
- learning systems
- computer vision
- image processing
- multiscale
- supervised learning
- qualitative models
- object oriented programming
- learning scheme
- multiple representations
- mobile learning
- unsupervised learning
- vision system
- artificial intelligence