Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training.
Longtian QiuShan NingXuming HePublished in: CoRR (2024)
Keyphrases
- fine grained
- coarse grained
- text mining
- image alignment
- image classification
- access control
- tightly coupled
- text documents
- input image
- image features
- image segmentation
- database
- free text
- training set
- web documents
- image retrieval
- test images
- information retrieval
- natural language processing
- distributed systems
- information extraction
- semantic information
- web images
- text processing