Automatic image caption generation using deep learning and multimodal attention.
Jin DaiXinyu ZhangPublished in: Comput. Animat. Virtual Worlds (2022)
Keyphrases
- deep learning
- input image
- image content
- image retrieval
- image segmentation
- image features
- multiscale
- image regions
- segmentation method
- image representation
- machine learning
- single image
- high resolution
- unsupervised learning
- similarity measure
- data mining
- segmentation algorithm
- face recognition
- learning algorithm
- lighting conditions
- unsupervised feature learning