Login / Signup
ViCLEVR: a visual reasoning dataset and hybrid multimodal fusion model for visual question answering in Vietnamese.
Khiem Vinh Tran
Hao Phu Phan
Kiet Van Nguyen
Ngan Luu-Thuy Nguyen
Published in:
Multim. Syst. (2024)
Keyphrases
</>
question answering
information retrieval
information extraction
visual features
fusion model
natural language processing
visual information
question classification
natural language
named entities
data mining
information fusion
syntactic information