bumjun_jung at VQA-Med 2020: VQA Model Based on Feature Extraction and Multi-modal Feature Fusion.
Bumjun JungLin GuTatsuya HaradaPublished in: CLEF (Working Notes) (2020)
Keyphrases
- multi modal
- feature fusion
- feature extraction
- image database
- human recognition
- multiple features
- fusion algorithm
- feature vectors
- image annotation
- dimensionality reduction
- subspace learning
- image processing
- principal component analysis
- high dimensional
- preprocessing
- wavelet transform
- image classification
- image data
- high resolution
- pattern recognition
- face recognition
- image content
- discriminant analysis
- classification accuracy
- data reduction
- single feature