SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification.
Jing ZhangYujin WangPublished in: SemEval@NAACL (2022)
Keyphrases
- input image
- image features
- single image
- image segmentation
- fusion method
- image content
- image analysis
- image data
- image representation
- multiscale
- image classification
- segmentation method
- text retrieval
- web images
- region of interest
- image retrieval
- image collections
- high resolution
- information retrieval
- image pixels
- low level
- information fusion
- test images
- similarity measure
- image regions
- edge detection
- multimodal image registration
- pixel values
- image fusion
- hough transform
- data fusion
- gray level
- feature points