.png){kind=icon}
返回
Cross-modal prototype learning for zero-shot handwritten character recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108859.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Traditional methods of handwritten character recognition rely on extensive labeled data. However, hu-mans can generalize to unseen handwritten characters by watching a few printed examples in textbooks. To simulate this ability, we propose a cross-modal prototype learning method (CMPL) to realize zero -shot recognition. For each character class, a prototype is generated by mapping the printed character into a deep neural network feature space. For unseen character class, its prototype can be directly pro-duced from a printed character sample, therefore, not requiring any handwritten samples to realize class -incremental learning. Specifically, CMPL considers different modalities simultaneously -online handwrit-ten trajectories, offline handwritten images, and auxiliary printed character images. The joint learning of the above modalities is achieved through sharing printed prototypes between online and offline data. In zero-shot inference, we feed CMPL the printed samples to obtain corresponding class prototypes, and then the unseen handwritten character can be recognized by the nearest prototype. Our experimental results demonstrate that CMPL outperforms the state-of-the-art methods in both online and offline zero -shot handwritten Chinese character recognition. Moreover, we also show the cross-domain generalization of CMPL from two perspectives: cross-language and modern-to-ancient handwritten character recogni-tion, focusing on the transferability between different languages and different styles (i.e., modern and historical handwritings).(c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Online handwriting
Offline handwriting
Printed character
Zero-shot
Prototype
Cross-modality
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Significance of elevated urinary N-acetyl-β-D-glucosaminidase activity in chronic cadmium poisoning
PREAI
分享收藏Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark在线和离线手写汉字识别: 综合研究和新基准.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏分享收藏Radical aggregation network for few-shot offline handwritten Chinese character recognition用于少镜头离线手写汉字识别的自由基聚合网络OAAI
OAAI分享收藏Building fast and compact convolutional neural networks for offline handwritten Chinese character recognitionPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Toward high-performance online HCCR: A CNN approach with DropDistortion, path signature and spatial stochastic max-pooling面向高性能在线HCCR: 具有DropDistortion，路径签名和空间随机最大池化的CNN方法OAAI
OAAI分享收藏Online and offline handwritten Chinese character recognition: Benchmarking on new databases在线和离线手写汉字识别: 新数据库的基准测试PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容