CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification.
Huidong LiuShaoyuan XuJinmiao FuYang LiuNing XieChien-Chih WangBryan WangYi SunPublished in: CoRR (2021)
Keyphrases
- text classification
- image data
- image features
- image content
- image analysis
- image classification
- multiscale
- single image
- input image
- video clips
- image representation
- high resolution
- bag of words
- image regions
- edge detection
- image matching
- image retrieval
- image segmentation
- image processing
- pixel values
- template matching
- feature selection
- neural network
- multi label
- spatial information
- region of interest
- segmentation method
- low level features
- object recognition
- step size