Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks
Not on the map. Why?
Abstract (arXiv)
Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular domains, namely graphs. Their success is highly dependent on how the topology of input graphs is defined and most of the existing GCN architectures rely on predefined or handcrafted graph structures. In this paper, we introduce a novel method that learns the topology (or connectivity) of input graphs as a part of GCN design. The main contribution of our method resides in building an orthogonal connectivity basis that optimally aggregates nodes, through their neighborhood, prior to achieve convolution. Our method also considers a stochasticity criterion which acts as a regularizer that makes the learned basis and the underlying GCNs lightweight while still being highly effective. Experiments conducted on the challenging task of skeleton-based hand-gesture recognition show the high effectiveness of the learned GCNs w.r.t. the related work.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 108 references that are in the map. First posted on arXiv 9 Apr 2021.
Builds on
47 of 108 references.
References · 47
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Mask R-CNNcited by 7,259
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2014Going Deeper with Convolutionscited by 4,231
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2015Fast R-CNNcited by 2,930
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
35 more
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
- 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
- 2018Deep Learning on Graphs: A Surveycited by 393
- 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
- 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
- 2019Learning Discrete Structures for Graph Neural Networkscited by 228
- 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
- 2019What graph neural networks cannot learn: depth vs widthcited by 195
- 2014Recurrent Neural Network Regularizationcited by 189
- 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
- 2016A Riemannian Network for SPD Matrix Learningcited by 162
- 2018Adaptive Graph Convolutional Neural Networkscited by 155
- 2016How to learn a graph from smooth signalscited by 146
- 2018Learning graphs from data: A signal representation perspectivecited by 119
- 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
- 2017Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networkscited by 92
- 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
- 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
- 2016Building Deep Networks on Grassmann Manifoldscited by 58
- 2018Learning to Solve NP-Complete Problems - A Graph Neural Network for Decision TSPcited by 58
- 2019A Unified Framework for Structured Graph Learning via Spectral Constraintscited by 53
- 2018Modular meta-learningcited by 51
- 2019Graph Element Networks: adaptive, structured computation and memorycited by 41
- 2016Learning heat diffusion graphscited by 39
- 2017Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Videocited by 30
- 2016Learning Sparse Graphs Under Smoothness Priorcited by 22
- 2016Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detectioncited by 18
- 2019Deep Iterative and Adaptive Learning for Graph Neural Networkscited by 17
- 2018Graph topology inference based on sparsifying transform learningcited by 10
- 2016Graph Learning from Data under Structural and Laplacian Constraintscited by 8
- 2019Product of Orthogonal Spheres Parameterization for Disentangled Representation Learningcited by 8
Built on by
Citing papers per year: 2024: 1.
1 paper.