Spatial-Temporal Aligned Multi-Agent Learning for Visual Dialog Systems.
Yong ZhuangTong YuJunda WuShiqu WuShuai LiPublished in: ACM Multimedia (2022)
Keyphrases
- spatial temporal
- multi agent learning
- dialog systems
- natural language generation
- temporal information
- action recognition
- spatial and temporal
- game theory
- visual features
- video shots
- natural language interfaces
- natural language
- visual information
- complex domains
- spatio temporal
- human computer
- multi agent
- artificial intelligence
- spatial information
- human actions
- conversational agents
- low level
- machine learning
- computer vision
- visual data
- knowledge base
- sensor networks