Self-Guiding Multimodal LSTM - When We Do Not Have a Perfect Training Dataset for Image Captioning.
Yang XianYingli TianPublished in: IEEE Trans. Image Process. (2019)
Keyphrases
- training dataset
- image analysis
- image data
- image features
- input image
- image retrieval
- region of interest
- image content
- segmentation method
- image segmentation
- multiscale
- single image
- image representation
- image classification
- test images
- image collections
- data sets
- knowledge discovery
- low level
- learning environment
- training data
- edge detection
- recurrent neural networks
- image pixels
- neural network
- feature points
- super resolution
- machine learning
- high resolution
- computer vision
- similarity measure