ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation.
Bo ZhangJian WangHui MaBo XuHongfei LinPublished in: ACM Multimedia (2023)
Keyphrases
- input image
- multiscale
- image data
- single image
- image classification
- image features
- image pixels
- template matching
- low level
- bayesian framework
- image retrieval
- registration framework
- image representation
- pixel values
- test images
- image content
- feature points
- image regions
- multi modal
- image registration
- image analysis
- face recognition
- edge detection
- image collections
- high resolution
- object recognition
- multiple modalities