University of Hildesheim at SemEval-2022 task 5: Combining Deep Text and Image Models for Multimedia Misogyny Detection.
Milan KalkeningsThomas MandlPublished in: SemEval@NAACL (2022)
Keyphrases
- multimedia
- input image
- image data
- multiscale
- image retrieval
- image analysis
- single image
- image classification
- test images
- image content
- e learning
- image collections
- image regions
- image features
- information retrieval
- multimedia search
- text detection
- bayesian framework
- image segmentation
- detection algorithm
- image search
- random fields
- bounding box
- object detectors
- complex background
- low level
- keywords
- digital libraries
- high resolution
- text information
- object detection