Improved Visual Story Generation with Adaptive Context Modeling.
Zhangyin FengYuchen RenXinmiao YuXiaocheng FengDuyu TangShuming ShiBing QinPublished in: ACL (Findings) (2023)
Keyphrases
- context modeling
- cross modal
- story generation
- context awareness
- petri net
- low level
- spatially adaptive
- multi modal
- visual recognition
- multimedia retrieval
- context aware
- ambient intelligence
- image coder
- visual data
- lossless compression
- high order
- computer vision
- visual information
- denoising
- video sequences
- feature extraction