PEVL

Back to List
method ID: pevl

Related Papers

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractVision-language pre-training (VLP) has shown impressive performance on a wide range of cross-modal tasks, where VLP models without reliance on object detectors are becoming the mainstream due to their superior …...

29956