Multi-modal transformer using two-level visual features for fake news detection.
Bin WangYong FengXiancai XiongYong-heng WangBaohua QiangPublished in: Appl. Intell. (2023)
Keyphrases
- multi modal
- visual features
- semantic concepts
- image annotation
- keywords
- image classification
- image search
- visual content
- visual information
- low level
- image retrieval
- low level features
- audio visual
- image collections
- multi modality
- automatic image annotation
- high dimensional
- web images
- semantic gap
- visual appearance
- key frames
- cross modal
- visual similarity
- video search
- visual data
- feature extraction
- audio features