SPLIT: Stance and Persuasion Prediction with Multi-modal on Image and Textual Information.
Jing ZhangShaojun YuXuan LiJia GengZhiyuan ZhengJoyce C. HoPublished in: ArgMining@EMNLP (2023)
Keyphrases
- multi modal
- textual information
- image content
- image data
- image features
- visual content
- textual and visual information
- multi modality
- multiscale
- visual information
- uni modal
- image annotation
- image collections
- image classification
- image representation
- web documents
- keywords
- semantic concepts
- image regions
- text documents
- image retrieval
- image segmentation
- co occurrence
- single modality
- image matching
- spatial relations
- feature selection
- text classification
- image database
- high dimensional