LocTex: Learning Data-Efficient Visual Representations
from Localized Textual Supervision
Zhijian Liu Simon Stent, Jie Li, John Gideon Song Han
MIT Toyota Research Institute MIT
https://loctex.mit.edu/
Abstract Image Caption Mouse Trace
There is a yellow
Computer vision tasks such as ...


雷达卡




京公网安备 11010802022788号







