VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
arXiv (Cornell University)(2022)
关键词
alignment,vision-language,weakly-supervised,local-feature
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要
arXiv (Cornell University)(2022)