YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding.
Kayode OlaleyeDan OneataHerman KamperPublished in: CoRR (2022)
Keyphrases
- cross lingual
- image dataset
- multi lingual
- machine translation
- image annotation
- image database
- language independent
- language modeling
- keywords
- automatic classification
- visual features
- cross lingual information retrieval
- text classification
- image collections
- visual information
- transfer learning
- news articles
- low level
- object recognition
- document clustering
- high level
- vector space
- feature selection
- language model
- face recognition
- decision trees