On Vision Features in Multimodal Machine Translation. ACL2022.

Release time:2024-01-09

Hits:

First Author:: Bei Li, Chuanhao Lv, Zefan Zhou, Tao Zhou, Tong Xiao, Anxiang Ma, JingBo Zhu.

Translation or Not:: no

Pre One:ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation. ACL2022.
Next One:Learning Multiscale Transformer Models for Sequence Generation. ICML2022.