MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning.
Wenqiao ZhangHaochen ShiJiannan GuoShengyu ZhangQingpeng CaiJuncheng LiSihui LuoYueting ZhuangPublished in: CoRR (2021)
Keyphrases
- image data
- input image
- image features
- image content
- single image
- relational graph
- multiscale
- image classification
- image analysis
- low level
- random fields
- image segmentation
- bayesian networks
- image representation
- high resolution
- computer vision
- edge detection
- image collections
- multi agent
- multimodal image registration
- multi modal
- segmentation algorithm
- segmentation method
- image regions
- similarity measure
- image search