Contextualized Keyword Representations for Multi-modal Retinal Image Captioning.
Jia-Hong HuangTing-Wei WuMarcel WorringPublished in: CoRR (2021)
Keyphrases
- multi modal
- retinal images
- blood vessels
- vessel segmentation
- optic disc
- keywords
- audio visual
- high dimensional
- retinal fundus
- multi modality
- diabetic retinopathy
- vascular tree
- video search
- retinal vessel
- retinal blood vessels
- optical coherence tomography
- cross modal
- high level
- computer assisted
- region of interest
- high resolution
- multiscale
- computer vision