Knowledge Commons of Institute of Automation,CAS
Image-to-Markup Generation via Paired Adversarial Learning | |
Jin-Wen Wu; Fei Yin; Yan-Ming Zhang; Xu-Yao Zhang; Cheng-Lin Liu | |
2018-09 | |
会议名称 | European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2018 |
会议日期 | 10-14 |
会议地点 | Dublin, Ireland |
摘要 | Motivated by the fact that humans can grasp semantic-invariant features shared by the same category while attention-based models focus mainly on discriminative features of each object, we propose a scalable paired adversarial learning (PAL) method for image-to-markup generation. PAL can incorporate the prior knowledge of standard templates to guide the attention-based model for discovering semantic-invariant features when the model pays attention to regions of interest. Furthermore, we also extend the convolutional attention mechanism to speed up the image-to-markup parsing process while achieving competitive performance compared with recurrent attention models. We evaluate the proposed method in the scenario of handwritten-image-to-LaTeX generation, i.e., converting handwritten mathematical expressions to LaTeX. Experimental results show that our method can significantly improve the generalization performance over standard attention-based encoder-decoder models. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/22093 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
作者单位 | NLPR, Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Jin-Wen Wu,Fei Yin,Yan-Ming Zhang,et al. Image-to-Markup Generation via Paired Adversarial Learning[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
-478880_1_En_2_Chapt(1138KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论