MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model.
Yatai JiJunjie WangYuan GongLin ZhangYanru ZhuHongfa WangJiaxing ZhangTetsuya SakaiYujiu YangPublished in: CVPR (2023)
Keyphrases
- experimental data
- theoretical analysis
- computer vision
- mathematical model
- natural language
- management system
- decision theory
- statistical model
- computational model
- prior knowledge
- probabilistic model
- probability distribution
- real time
- objective function
- training samples
- parameter estimation
- similarity measure
- image sequences
- high level
- decision trees
- conceptual model
- formal model
- context dependent
- decision making
- specification language