[D-20] 情報論的学習理論と機械学習

10:15 AM - 10:30 AM JST(1:15 AM - 1:30 AM UTC)

[D-20-06] An Empirical Study of Pretraining to Enhance Embedding Alignment in Vision-and-Language Models

○Satoshi Kawamura¹, Kohei Yamamoto¹, Mariko Tomariguchi¹, Hideaki Tamai¹ (1. OKI)

Keywords:

Vision-and-Language Models,multimodal,alignment