Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task.
Ting HanDavid SchlangenPublished in: IJCNLP(2) (2017)
Keyphrases
- image description
- image data
- input image
- single image
- image content
- image features
- image segmentation
- image retrieval
- high level
- multiscale
- grey level
- low level
- test images
- image analysis
- template matching
- image representation
- edge detection
- hough transform
- image classification
- computer vision
- pixel values
- image synthesis
- multimodal image registration
- semantic description
- image collections
- region of interest
- image matching
- segmentation algorithm
- digital images
- high resolution