Aligning Visual Regions and Textual Concepts: Learning Fine-Grained Image Representations for Image Captioning.
Fenglin LiuYuanxin LiuXuancheng RenKai LeiXu SunPublished in: CoRR (2019)
Keyphrases
- fine grained
- image representation
- image features
- image classification
- image content
- multiscale
- input image
- region segmentation
- image retrieval
- coarse grained
- feature representations
- image regions
- visual concepts
- bag of words
- scene classification
- access control
- image segmentation
- sparse coding
- receptive fields
- visual features
- sparse representation
- feature space
- low level
- visual words
- visual recognition
- visual vocabulary
- visual content
- image collections
- image database
- image structure
- visual information
- image registration
- keypoints
- object recognition