Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning.
Naeha SharifMohammad A. A. K. JalwanaMohammed BennamounWei LiuSyed Afaq Ali ShahPublished in: IVCNZ (2020)
Keyphrases
- spatial relations
- multiscale
- image features
- image analysis
- keypoints
- image data
- normalized correlation
- multiple objects
- image classification
- image segmentation
- input image
- image regions
- region of interest
- edge detection
- pixel level
- target object
- image representation
- single image
- high resolution
- image content
- test images
- partial occlusion
- object models
- image retrieval
- background clutter
- object localization
- location and orientation
- object recognition
- individual objects
- object features
- complex scenes
- lighting conditions
- position and orientation
- bounding box
- intensity images
- spatial relationships
- image set
- visual appearance
- object representation
- segmentation method
- color histogram
- similar objects
- feature points
- low level
- object detection