UMUTeam at SemEval-2022 Task 5: Combining image and textual embeddings for multi-modal automatic misogyny identification.
José Antonio García-DíazCamilo Caparrós-LaizRafael Valencia-GarcíaPublished in: SemEval@NAACL (2022)
Keyphrases
- multi modal
- uni modal
- input image
- image data
- image analysis
- image features
- multiscale
- image retrieval
- image representation
- image segmentation
- cross modal
- image classification
- multi modality
- auto annotation
- image content
- low level
- high dimensional
- high resolution
- fusing multiple
- image collections
- low dimensional
- image regions
- multimedia
- fully automatic
- image annotation
- segmentation method
- audio visual
- video search
- image processing
- edge detection
- single modality
- keywords
- high level