CASIA-IVA-Lab/M3VQA
收藏Hugging Face2026-04-20 更新2026-04-26 收录
下载链接：
https://hf-mirror.com/datasets/CASIA-IVA-Lab/M3VQA
下载链接
链接失效反馈官方服务：
资源简介：
---
configs:
- config_name: default
data_files:
- split: test
path: quesions.jsonl
license: mit
---
# M<sup>3</sup>-VQA
This is the official dataset for the paper "M<sup>3</sup>-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering" (ACL2026main).
[[Paper]]() [[Code]](https://github.com/CASIA-IVA-Lab/M3VQA) [[Dataset]](https://huggingface.co/datasets/CASIA-IVA-Lab/M3VQA)
See [[Code]](https://github.com/CASIA-IVA-Lab/M3VQA) for more details.
If you find this work helpful, please cite using this BibTeX:
```
```
提供机构：
CASIA-IVA-Lab
