TVLT: Textless Vision-Language Transformer.
Zineng TangJaemin ChoYixin NieMohit BansalPublished in: NeurIPS (2022)
Keyphrases
- computer vision
- natural language
- programming language
- english language
- language processing
- vision system
- fuzzy logic
- image processing
- language learning
- data sets
- computational linguistics
- neural network
- databases
- fault diagnosis
- decision making
- real time
- visual perception
- active vision
- database
- machine learning
- bayesian networks
- programming environment
- linguistic knowledge
- operational semantics