Filters








12,121 Hits in 5.2 sec

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification [article]

Lu Bail, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock
2019 arXiv   pre-print
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification.  ...  Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures.  ...  The aim of this paper is to develop a new Graph Convolutional Network (GCN) model to learn effective features for graph classification.  ... 
arXiv:1904.04238v2 fatcat:qextujhehjarfkllqqqtoqm4ou

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin Hancock
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification.  ...  Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures.  ...  ACKNOWLEDGMENTS This work is supported by the National Natural Science Foundation of China (Grant no. 61976235 and 61602535), the program for innovation research in Central University of Finance and Economics  ... 
doi:10.1109/tpami.2020.3011866 pmid:32750832 fatcat:rqroqwb2njdtxkl2c4bocaxdxy

Graph Convolutional Neural Networks based on Quantum Vertex Saliency [article]

Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui, Jian Cheng, Edwin R. Hancock
2019 arXiv   pre-print
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes.  ...  the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications.  ...  that integrates the graph representation and learning in both the quantum spatial graph convolution layer and the traditional convolution layer for graph classification problems.  ... 
arXiv:1809.01090v2 fatcat:t4snzjrdwrh6nikekskkndv3he

Learning Vertex Convolutional Networks for Graph Classification [article]

Lu Bai, Lixin Cui, Shu Wu, Yuhang Jiao, Edwin R. Hancock
2019 arXiv   pre-print
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification.  ...  Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution  ...  Learning Vertex Convolutional Networks In this section, we develop a new vertex convolutional network model for graph classification.  ... 
arXiv:1902.09936v1 fatcat:iib4dt3qurecxkcefwtvgvayl4

Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network [article]

Ji Gan, Weiqiang Wang, Ke Lu
2020 arXiv   pre-print
Accordingly, we propose a novel spatial graph convolution network (SGCN) to effectively classify those character graphs for the first time.  ...  Specifically, our SGCN incorporates the local neighbourhood information via spatial graph convolutions and further learns the global shape properties with a hierarchical residual structure.  ...  orders by viewing characters as graphs. • We propose a novel spatial graph convolutional network (SGCN) for OLHCCR for the first time.  ... 
arXiv:2004.09412v1 fatcat:tp3jykja2zftdb7ww3dytm77ny

Can Graph Convolution Networks Learn Spatial Relations?

Azelle Courtial, Guillaume Touya, Xiang Zhang
2021 Abstracts of the International Cartographic Association  
Hence, our experiments constitute a first step in exploring the capability of deep neural network for learning representations of spatial relations.  ...  The goal of this paper is to illustrate the potential of graph convolutional networks (GCN) for the identification of patterns and relations important for map generalisation with two use cases: building  ... 
doi:10.5194/ica-abs-3-60-2021 fatcat:g7prrpuq2zh7jiq7ryl7qt3gpe

Spectral Graph Transformer Networks for Brain Surface Parcellation [article]

Ran He, Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2019 arXiv   pre-print
The novel Spectral Graph Transformer (SGT) network proposed in this paper uses very few randomly sub-sampled nodes in the spectral domain to learn the alignment matrix for multiple brain surfaces.  ...  We validate the use of this SGT network along with a graph convolution network to perform cortical parcellation.  ...  In an alternative application for natural image classification, [15] proposes a transformer network for CNNs for learning a transformation matrix to spatially standardize the image data.  ... 
arXiv:1911.10118v1 fatcat:lqmz45olabdddiqjx66fjcv76y

SelfSAGCN: Self-Supervised Semantic Alignment for Graph Convolution Network

Xu Yang, Cheng Deng, Zhiyuan Dang, Kun Wei, Junchi Yan
2021 Computer Vision and Pattern Recognition  
Graph convolution networks (GCNs) are a powerful deep learning approach and have been successfully applied to representation learning on graphs in a variety of realworld applications.  ...  In this paper, we propose a simple yet effective Self-Supervised Semantic Alignment Graph Convolution Network (SelfSAGCN), which consists of two crux techniques: Identity Aggregation and Semantic Alignment  ...  [13] proposed a simple Graph Convolutional Network (GCN) for semi-supervised learning.  ... 
dblp:conf/cvpr/0019DDWY21 fatcat:kv2w2rfb2fhvjf3p6stbsy6tya

Dynamic Graph Warping Transformer for Video Alignment

Junyan Wang, Yang Long, Maurice Pagnucco, Yang Song
2021 British Machine Vision Conference  
Our approach is the first Graph Transformer framework designed for video analysis and alignment.  ...  Existing methods are typically based on supervised learning to align video frames according to annotated action phases.  ...  Specifically, Graph Convolutional Networks (GCNs) [7, 8, 9, 14] can learn local and global structural patterns of graphs with convolutional functions.  ... 
dblp:conf/bmvc/Wang0P021 fatcat:worfhpf3fjclxkp4o5iqdsqaee

Continuous Sign Language Recognition Based on Spatial-Temporal Graph Attention Network

Qi Guo, Shujun Zhang, Hui Li
2023 CMES - Computer Modeling in Engineering & Sciences  
We adopted BLSTM to learn the long-term dependence and connectionist temporal classification to align the word-level sequences.  ...  The graph-based multihead attention mechanism is utilized with adjacent matrix calculation for better local-feature exploration, and short-term motion correlation modeling is completed via a temporal convolutional  ...  Therefore, researchers combined graph and deep learning, generating GNNs, including graph convolution network (GCN) and GAT.  ... 
doi:10.32604/cmes.2022.021784 fatcat:jcroo2nenrblzflz24dkeeht74

Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [article]

Kai Zhang, Yaokang Zhu, Jun Wang, Jie Zhang, Hongyuan Zha
2020 arXiv   pre-print
Graph neural networks are promising architecture for learning and inference with graph-structured data.  ...  We analyze the intrinsic difficulty in graph classification under the unified concept of "resolution dilemmas" with learning theoretic recovery guarantees, and propose "SLIM", an inductive neural network  ...  Spatial Resolution Diminishes in Graph Pooling Graph neural networks (GNN) for graph classification typically has two stages: graph convolution and graph pooling [14, 38] .  ... 
arXiv:2006.15763v1 fatcat:yr32pvskfzfnlcphf55gvniqxa

Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentation [article]

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2020 arXiv   pre-print
In this paper, adversarial training is exploited to learn surface data across inconsistent graph alignments.  ...  Recent developments have enabled learning surface data directly across multiple brain surfaces via graph convolutions on cortical data.  ...  We gratefully acknowledge the support of NVIDIA Corporation for the donation of the Titan X Pascal GPU used for this research.  ... 
arXiv:2004.00074v1 fatcat:fi5psaaorzarrgsix2aabuceni

SAST-GCN: Segmentation Adaptive Spatial Temporal-Graph Convolutional Network for P3-Based Video Target Detection

Runnan Lu, Ying Zeng, Rongkai Zhang, Bin Yan, Li Tong
2022 Frontiers in Neuroscience  
This paper proposes a segmentation adaptive spatial-temporal graph convolutional network (SAST-GCN) for P3-based video target detection.  ...  Then, the spatial-temporal feature of EEG data is extracted by adaptive spatial-temporal graph convolution to discriminate the target and non-target in the video.  ...  were mainly responsible for research design. LT was mainly responsible for data collection and manuscript modification. All authors contributed to the article and approved the submitted version.  ... 
doi:10.3389/fnins.2022.913027 pmid:35720707 pmcid:PMC9201684 fatcat:apgatuvt7jdrdkwrrhwzczaghy

Graph Convolutions on Spectral Embeddings: Learning of Cortical Surface Data [article]

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2018 arXiv   pre-print
Direct learning of surface data via graph convolutions would provide a new family of fast algorithms for processing brain surfaces.  ...  This paper leverages recent advances in spectral graph matching to transfer surface data across aligned spectral domains.  ...  Conclusion This paper presented a novel framework for learning surface data via spectral graph convolutions.  ... 
arXiv:1803.10336v1 fatcat:mvcxhzeuqzcvdolw3j3n4t3lxm

Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification

Ziyu Jia, Youfang Lin, Jing Wang, Xiaojun Ning, Yuanlai He, Ronghao Zhou, Yuhan Zhou, Li-Wei H Lehman
2021 IEEE transactions on neural systems and rehabilitation engineering  
To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification.  ...  The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages.  ...  Then, an attention based spatial-temporal graph convolution is designed for the most relevant spatial-temporal features for sleep stage classification.  ... 
doi:10.1109/tnsre.2021.3110665 pmid:34487495 pmcid:PMC8556658 fatcat:kdpmv65nlfd6jiggqkicjsogvq
« Previous Showing results 1 — 15 out of 12,121 results