M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation.
Hongcheng LiuPingjie WangYu WangYanfeng WangPublished in: CoRR (2024)
Keyphrases
- probabilistic model
- prior knowledge
- formal model
- probability distribution
- conceptual model
- management system
- video sequences
- expert knowledge
- domain knowledge
- real time
- knowledge based systems
- knowledge acquisition
- formal representation
- statistical model
- mathematical model
- computational model
- human computer interaction
- multi modal
- knowledge representation
- natural language
- learning environment
- multimedia