Login / Signup
Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding.
Dexin Wang
Deyi Xiong
Published in:
AAAI (2021)
Keyphrases
</>
object level
machine translation
low level
high level
natural language processing
cross modal
pixel level
information extraction
object class
multi modal
higher level
visual information
visual data
image processing
multimedia