CISum: Learning Cross-modality Interaction to Enhance Multimodal Semantic Coverage for Multimodal Summarization.
Litian ZhangXiaoming ZhangZiming GuoZhipeng LiuPublished in: CoRR (2023)
Keyphrases
- multimodal interaction
- multi modal
- online learning
- supervised learning
- reinforcement learning
- unsupervised learning
- semantic web
- learning process
- learning systems
- audio visual
- inductive inference
- multimedia
- prior knowledge
- multi agent systems
- natural language processing
- learning algorithm
- human computer interaction
- visual information
- semantic network