mlsanityData to 7 Oct 2026

A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition

arXiv 2111.06995 ↗First posted 13 Nov 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available at https://github.com/iesymiao/CD-GCN.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 13 Nov 2021.

Builds on

20 of 42 references.

References · 20

  1. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  2. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  3. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  4. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  5. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  6. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  7. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  8. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
  9. 2018Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learningcited by 47
  10. 2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
  11. 2020AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searchingcited by 39
  12. 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37
8 more
  1. 2020Multi-Modal Face Anti-Spoofing Based on Central Difference Networkscited by 36
  2. 2020Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognitioncited by 36
  3. 2020Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognitioncited by 36
  4. 2016Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networkscited by 32
  5. 2019Skeleton-Based Online Action Prediction Using Scale Selection Networkcited by 20
  6. 2016RGB-D-based Action Recognition Datasets: A Surveycited by 14
  7. 2017Skeleton-based Action Recognition Using LSTM and CNNcited by 10
  8. 2020SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searchingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 2.

6 papers.

  1. 2024Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignmentcited by 9
  2. 2025MoFM: A Large-Scale Human Motion Foundation Modelcited by 5
  3. 2024Joint Temporal Pooling for Improving Skeleton-based Action Recognitioncited by 3
  4. 2023From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learningcited by 1
  5. 2023SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognitioncited by 0
  6. 2025HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 0