Tackling Vision Language Tasks Through Learning Inner Monologues.
Diji YangKezhen ChenJinmeng RaoXiaoyuan GuoYawen ZhangJie YangYi ZhangPublished in: CoRR (2023)
Keyphrases
- knowledge acquisition
- prior knowledge
- multiple tasks
- learning algorithm
- image processing
- learning process
- real time
- learning systems
- supervised learning
- neural network
- learning tasks
- unsupervised learning
- language acquisition
- artificial intelligence
- learning mechanisms
- language learners
- learning scheme
- learning community
- vision system
- mobile robot
- mobile devices
- machine learning