lbw18601752667/IDMR-train
收藏官方服务：
资源简介：
IDMR数据集是一个用于实例驱动的多模态检索的训练数据集，它支持跨多种模态源的大规模训练。该数据集适用于进行跨数据集多模态检索、实例驱动的对齐以及跨异质域（如VQA、grounding等）的迁移研究。
The IDMR dataset is a training dataset for instance-driven multimodal retrieval, supporting large-scale training across diverse multimodal sources. It is suitable for research on cross-dataset multimodal retrieval, instance-driven alignment, and transfer across heterogeneous domains such as VQA, grounding, etc.
提供机构：
lbw18601752667
