DSSE-200
收藏资源简介:
displayName: DSSE-200 labelTypes: - Semantic_seg_map license: - Unknown mediaTypes: - Image paperUrl: http://openaccess.thecvf.com/content_cvpr_2017/papers/Yang_Learning_to_Extract_CVPR_2017_paper.pdf publishDate: "2017" publishUrl: http://personal.psu.edu/xuy111/projects/cvpr2017_doc.html publisher: - Adobe Research - Pennsylvania State University tags: - Documents - Picture taskTypes: - Semantic Segmentation - Document Layout --- # 数据集介绍 ## 简介 DSSE-200 是一个复杂的文档布局数据集,包括各种数据集样式。该数据集包含来自图片、PPT、宣传册文档、旧报纸和扫描文档的 200 张图像。 ## 引文 ``` @inproceedings{yang2017learning, title={Learning to extract semantic structure from documents using multimodal fully convolutional neural networks}, author={Yang, Xiao and Yumer, Ersin and Asente, Paul and Kraley, Mike and Kifer, Daniel and Lee Giles, C}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={5315--5324}, year={2017} } ``` ## Download dataset :modelscope-code[]{type="git"}
displayName: DSSE-200 labelTypes: - 语义分割图(Semantic_seg_map) license: - 未知 mediaTypes: - 图像 paperUrl: http://openaccess.thecvf.com/content_cvpr_2017/papers/Yang_Learning_to_Extract_CVPR_2017_paper.pdf publishDate: "2017" publishUrl: http://personal.psu.edu/xuy111/projects/cvpr2017_doc.html publisher: - Adobe研究院(Adobe Research) - 宾夕法尼亚州立大学(Pennsylvania State University) tags: - 文档 - 图像 taskTypes: - 语义分割(Semantic Segmentation) - 文档布局(Document Layout) --- # 数据集介绍 ## 简介 DSSE-200 是一款复杂的文档布局数据集,涵盖多种文档样式。该数据集共包含200幅图像,素材来源涵盖普通图像、PPT演示文稿、宣传册、旧报纸及扫描文档。 ## 引用 @inproceedings{yang2017learning, title={Learning to extract semantic structure from documents using multimodal fully convolutional neural networks}, author={Yang, Xiao and Yumer, Ersin and Asente, Paul and Kraley, Mike and Kifer, Daniel and Lee Giles, C}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={5315--5324}, year={2017} } ## 数据集下载 :modelscope-code[]{type="git"}




