Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question Answering.
Hiba MaryamLing FuJiajun SongTajrian ABM ShafayetQidi LuoXiang BaiYuliang LiuPublished in: CoRR (2024)
Keyphrases
- question answering
- natural scenes
- text detection
- natural images
- text regions
- object recognition
- information retrieval
- visual attention
- information extraction
- video analysis
- image content
- named entities
- natural language
- natural language processing
- visual information
- text information
- image structure
- text lines
- saliency map
- video database
- visual features
- action recognition
- computer vision
- higher order
- outdoor scenes
- machine learning
- feature selection
- feature set
- image data
- feature space
- multiscale
- image sequences