Long-Range Graph U-Nets: Node and Edge Clustering Pooling Model For Stroke Classification in Online Handwritten Documents

Muwu Yao, Shuang She, Jinrong Li, Jianmin Lin, Ming Yang, Hongxing Peng
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1542-1557, 2024.

Abstract

Stroke classification is a crucial step for applications with online handwritten input. It is a challenging task due to the variations in writing style, complex structure, long contextual semantic dependence of written content and etc. In this work, we propose a method called Long-Range Graph U-Nets, which involves using a novel node and edge clustering graph pooling layer in the encoder block and a multi-level feature fusion strategy. Such operations guide the model to leverage both temporal and spatial contextual information, establish long-range semantic dependencies, and effectively reduce redundant information caused by local instances of the same category. Extensive experiments conducted on publicly available online handwritten document datasets, demonstrate that our proposed method outperforms previous methods by a significant margin, particularly in the List category, and achieves state-of-the-art performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-yao24a, title = {{Long-Range Graph U-Nets}: {N}ode and Edge Clustering Pooling Model For Stroke Classification in Online Handwritten Documents}, author = {Yao, Muwu and She, Shuang and Li, Jinrong and Lin, Jianmin and Yang, Ming and Peng, Hongxing}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1542--1557}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/yao24a/yao24a.pdf}, url = {https://proceedings.mlr.press/v222/yao24a.html}, abstract = {Stroke classification is a crucial step for applications with online handwritten input. It is a challenging task due to the variations in writing style, complex structure, long contextual semantic dependence of written content and etc. In this work, we propose a method called Long-Range Graph U-Nets, which involves using a novel node and edge clustering graph pooling layer in the encoder block and a multi-level feature fusion strategy. Such operations guide the model to leverage both temporal and spatial contextual information, establish long-range semantic dependencies, and effectively reduce redundant information caused by local instances of the same category. Extensive experiments conducted on publicly available online handwritten document datasets, demonstrate that our proposed method outperforms previous methods by a significant margin, particularly in the List category, and achieves state-of-the-art performance.} }
Endnote
%0 Conference Paper %T Long-Range Graph U-Nets: Node and Edge Clustering Pooling Model For Stroke Classification in Online Handwritten Documents %A Muwu Yao %A Shuang She %A Jinrong Li %A Jianmin Lin %A Ming Yang %A Hongxing Peng %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-yao24a %I PMLR %P 1542--1557 %U https://proceedings.mlr.press/v222/yao24a.html %V 222 %X Stroke classification is a crucial step for applications with online handwritten input. It is a challenging task due to the variations in writing style, complex structure, long contextual semantic dependence of written content and etc. In this work, we propose a method called Long-Range Graph U-Nets, which involves using a novel node and edge clustering graph pooling layer in the encoder block and a multi-level feature fusion strategy. Such operations guide the model to leverage both temporal and spatial contextual information, establish long-range semantic dependencies, and effectively reduce redundant information caused by local instances of the same category. Extensive experiments conducted on publicly available online handwritten document datasets, demonstrate that our proposed method outperforms previous methods by a significant margin, particularly in the List category, and achieves state-of-the-art performance.
APA
Yao, M., She, S., Li, J., Lin, J., Yang, M. & Peng, H.. (2024). Long-Range Graph U-Nets: Node and Edge Clustering Pooling Model For Stroke Classification in Online Handwritten Documents. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1542-1557 Available from https://proceedings.mlr.press/v222/yao24a.html.

Related Material