arXiv Computer Vision· Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yazhe Hu, Lan Guo, Yuying Wang, Mengqing Guo, Bhavesh Dnyaneshwar Gore, Shubham Pathak, Ramapriya Ranganath, Sandeep Sharma, Tao Sheng, Sujith Ravi, Dan Roth·· 2 小时前AI 评分22
VELD-QA：面向长文档视觉证据定位与问答的大规模数据集
VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
AI 导读
VELD-QA 是一个面向长文档视觉证据定位与问答的大规模基准，包含 15,000 个人工编写问答对，覆盖 5,859 份真实 PDF、共 372,445 页，均衡图表、表格与复杂版式任务。
来源：arXiv Computer Vision · arxiv.org