Does Multimodality Help Human and Machine for Translation and Image Captioning?
Ozan CaglayanWalid AransaYaxing WangMarc MasanaMercedes García-MartínezFethi BougaresLoïc BarraultJoost van de WeijerPublished in: WMT (2016)
Keyphrases
- image data
- input image
- image content
- multiscale
- image features
- image analysis
- low level
- image representation
- image collections
- static images
- image retrieval
- template matching
- image pixels
- test images
- image matching
- segmentation method
- edge detection
- image segmentation
- keypoints
- hough transform
- human visual
- feature points
- image classification
- region of interest
- high resolution
- similarity measure
- image processing
- human observers
- visual attributes
- grey level
- lighting conditions
- vector field
- spatial information
- image regions