Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning.
Shivaen RamshettyGaurav VermaSrijan KumarPublished in: CoRR (2023)
Keyphrases
- language learning
- cross modal
- multi modal
- computer vision
- multimedia retrieval
- foreign language
- language acquisition
- computer assisted language learning
- mobile learning
- image retrieval
- multimedia databases
- visual recognition
- visual similarity
- mobile language learning
- language learners
- visual data
- native speakers
- language skills
- context aware
- database
- vocabulary learning