MIMOSA: Human-AI Co-Creation of Computational Spatial Audio Effects on Videos.
Zheng NingZheng ZhangJerrick BanKaiwen JiangRuohong GanYapeng TianToby Jia-Jun LiPublished in: CoRR (2024)
Keyphrases
- computational models
- artificial intelligence
- human activities
- multimedia
- video sequences
- artificially intelligent
- human cognitive
- human intelligence
- human language
- computational systems
- spatial information
- visual data
- signal processing
- machine learning
- expert systems
- knowledge representation
- video content analysis
- video surveillance
- spatio temporal patterns
- video database
- audio features
- space time
- motion cues
- human level
- spatial data
- motion capture data
- temporal domain
- video frames
- cognitive psychology
- spatio temporal
- audio visual
- visual information
- ai systems
- temporal relationships
- human cognition
- static images
- human actions
- low level
- intelligent systems
- case based reasoning