MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks.
TMLR 2024(2024)
关键词
Multimodal Fusion,Feature Matching,Visual Question Answering,Cross-Modal Retrieval,Representation Learning
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
TMLR 2024(2024)