跳到正文
arXiv · 机器人与计算机视觉· Byeongju Woo, Zilin Wang, Byeonghyun Pak, Sangwoo Mo, Stella X. Yu·· 8 天前AI 评分68

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

AI 导读

该论文提出 CAFT(Cross-domain Alignment of Forest and Trees)视觉语言模型,旨在解决现有模型难以忠实理解长细节丰富描述的问题。

来源:arXiv · 机器人与计算机视觉 · arxiv.org