Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering.
Yifan DongSuhang WuFandong MengJie ZhouXiaoli WangJianxin LinJinsong SuPublished in: ACM Multimedia (2023)
Keyphrases
- multi modal
- noise filtering
- multi granularity
- single modality
- input image
- uni modal
- image classification
- noise reduction
- image analysis
- multiscale
- edge detection
- post processing
- image segmentation
- data mining
- visual features
- pixel values
- contrast enhancement
- low signal to noise ratio
- color images
- denoising
- database
- decision trees
- computer vision
- machine learning