Crossmark

Visionary: vision-aware enhancement with reminding scenes generated by captions via multimodal transformer for embodied referring expression

Published Online: 2024-05-30

Published Print: 2025-02

Authors

Yuan, Zhengwu

Tang, Peixian

Sang, Xinguang

Zhang, Fan

Zhang, Zheqi
Funding

Funding for this research was provided by:

Chongqing Municipal Education Commission (HZ2021008)
License Information

Text and Data Mining valid from 2024-05-30

Version of Record valid from 2024-05-30
More Information

Article History

Accepted: 6 May 2024

First Online: 30 May 2024

Declarations

:

: The authors declared no potential conflict of interest.

Document is current