Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Veselý, Marcel"'
The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is carried out
Externí odkaz:
http://arxiv.org/abs/2401.16575