Image-to-Markup Generation via Paired Adversarial Learning
文献类型：会议论文
| 作者 | Jin-Wen Wu ; Fei Yin; Yan-Ming Zhang; Xu-Yao Zhang; Cheng-Lin Liu
|
| 出版日期 | 2018-09 |
| 会议日期 | 10-14 |
| 会议地点 | Dublin, Ireland |
| 英文摘要 | 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. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/22093]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
| 作者单位 | NLPR, Institute of Automation, Chinese Academy of Sciences |
| 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]. 见:. Dublin, Ireland. 10-14. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。