A Hierarchical Multimodal Attention-based Neural Network for Image Captioning.
Yong ChengFei HuangLian ZhouCheng JinYuejie ZhangTao ZhangPublished in: SIGIR (2017)
Keyphrases
- neural network
- image data
- image analysis
- template matching
- input image
- image content
- image features
- image representation
- single image
- multiscale
- multi modal
- image regions
- image classification
- segmentation method
- region of interest
- image collections
- image segmentation
- image retrieval
- similarity measure
- keypoints
- edge detection
- spatial information
- image pixels
- binary images
- hough transform
- low level
- artificial neural networks
- lighting conditions
- neural network model
- multi layer