Exploring the Trade-Off within Visual Information for MultiModal Sentence Summarization.
Minghuan YuanShiyao CuiXinghua ZhangShicheng WangHongbo XuTingwen LiuPublished in: SIGIR (2024)
Keyphrases
- visual information
- trade off
- audio visual
- text summarization
- automatic summarization
- visual features
- visual content
- multi document summarization
- low level
- sentence extraction
- document summaries
- visual cues
- automatic text summarization
- visual data
- multidocument summarization
- single document summarization
- natural language
- eye movements
- content based image retrieval systems
- semantic information
- content based image
- machine learning
- human visual system
- natural language processing
- visual information retrieval
- image processing
- information extraction
- visual scene
- image classification
- image collections
- multi modal
- question answering
- textual information
- low level features