Evaluating Automatically Generated Phoneme Captions for Images.
Justin van der HoutZoltán D'HaeseMark Hasegawa-JohnsonOdette ScharenborgPublished in: CoRR (2020)
Keyphrases
- automatically generated
- image data
- image features
- automatically generate
- ground truth
- input image
- image database
- automatically generating
- image collections
- image classification
- image retrieval
- manually generated
- manually constructed
- edge detection
- image annotation
- image registration
- automatically created
- visual features
- segmentation algorithm
- speech recognition
- language model
- information retrieval
- domain specific
- natural language processing
- high resolution
- image segmentation