BByrneLab/multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR_CN

M2KR是一个用于多模态知识检索的基准数据集，包含用于训练和评估多模态知识检索模型的任务和数据集集合。数据集包含三种任务类型：图像到文本检索（I2T）、问题到文本检索（Q2T）以及图像和问题到文本检索（IQ2T）。数据集的主要用途是用于预训练通用多模态知识检索模型并评估其性能。

M2KR is a benchmark dataset for multimodal knowledge retrieval, containing a collection of tasks and datasets for training and evaluating multimodal knowledge retrieval models. The datasets are pre-processed into a uniform format and several task-specific prompting instructions are written. The M2KR benchmark includes three types of tasks: Image to Text (I2T) retrieval, Question to Text (Q2T) retrieval, and Image & Question to Text (IQ2T) retrieval. The dataset is primarily intended for pretraining and benchmarking multimodal knowledge retrieval models, targeting researchers and hobbyists in the fields of computer vision, natural language processing, machine learning, and artificial intelligence.