VisualGPTScore: Visio-Linguistic Reasoning with Multimodal Generative Pre-Training Scores.
Zhiqiu LinXinyue ChenDeepak PathakPengchuan ZhangDeva RamananPublished in: CoRR (2023)
Keyphrases
- human reasoning
- training process
- knowledge representation
- multimodal interaction
- discriminative classifiers
- training phase
- natural language
- discriminative training
- approximate reasoning
- multi modal
- online learning
- natural language processing
- training set
- knowledge base
- training samples
- ranked list
- database management systems
- fuzzy logic