Evaluating Automatically Generated Phoneme Captions for Images.
Justin van der HoutZoltán D'HaeseMark Hasegawa-JohnsonOdette ScharenborgPublished in: INTERSPEECH (2020)
Keyphrases
- automatically generated
- automatically generate
- image data
- input image
- image database
- manually constructed
- ground truth
- image features
- image registration
- edge detection
- fully automatic
- image retrieval
- image collections
- manually created
- speech recognition
- image annotation
- manually generated
- image classification
- automatically generating
- segmentation algorithm
- knowledge base
- general purpose
- metadata