Understanding News Text and Images Connection with Context-enriched Multimodal Transformers.
Cláudio BartolomeuRui NóbregaDavid SemedoPublished in: ACM Multimedia (2022)
Keyphrases
- image data
- image database
- image classification
- image features
- text detection
- three dimensional
- web images
- text extraction
- object recognition
- image analysis
- text information
- input image
- image registration
- ground truth
- social media
- image matching
- image annotation
- textual information
- edge detection
- multi modal
- image retrieval
- segmentation method
- keywords
- information retrieval
- news video
- multimodal image registration
- complex background
- contextual information
- image processing