Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network.
Jiajun WeiHongjian ZhanYue LuXiao TuBing YinCong LiuUmapada PalPublished in: AAAI (2024)
Keyphrases
- programming language
- image data
- computer vision
- multiscale
- language learning
- image analysis
- region of interest
- image retrieval
- input image
- image classification
- natural language
- image features
- low level image processing
- segmentation algorithm
- low level
- high level
- image segmentation
- edge detection
- feature points
- single image
- spatial information
- image matching
- image processing
- social networks
- image collections
- visual perception
- neural network