A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation.
Yupan HuangBei LiuJianlong FuYutong LuPublished in: CoRR (2021)
Keyphrases
- image analysis
- image database
- three dimensional
- image classification
- input image
- image data
- image features
- image retrieval
- region of interest
- ground truth
- image registration
- image content
- real world
- lighting conditions
- rigid body
- complex background
- test images
- textual descriptions
- n gram
- language model
- object recognition
- keywords
- similarity measure
- computer vision