mlsanityData to 14 Oct 2026

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

arXiv 2207.12100 ↗First posted 25 Jul 2022cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for skeleton-based interaction recognition via modeling the interactive body parts as graphs. More specifically, the proposed IGFormer constructs interaction graphs according to the semantic and distance correlations between the interactive body parts, and enhances the representation of each person by aggregating the information of the interactive body parts based on the learned graphs. Furthermore, we propose a Semantic Partition Module to transform each human skeleton sequence into a Body-Part-Time sequence to better capture the spatial and temporal information of the skeleton sequence for learning the graphs. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art with a significant margin.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 25 Jul 2022.

Builds on

25 of 36 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  5. 2021ViViT: A Video Vision Transformercited by 1,620
  6. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  7. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  8. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  9. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  10. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  11. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  12. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
13 more
  1. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  2. 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 143
  3. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  4. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  5. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  6. 2020Skeleton-based Action Recognition via Spatial and Temporal Transformer Networkscited by 98
  7. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 89
  8. 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
  9. 2017Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networkscited by 62
  10. 2019Interaction Relational Network for Mutual Action Recognitioncited by 27
  11. 2017Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnncited by 26
  12. 2017Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognitioncited by 23
  13. 2019Skeleton-Based Online Action Prediction Using Scale Selection Networkcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 9; 2025: 7; 2026: 7.

31 papers.

Sort:

By area:

  1. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  2. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 47
  3. 2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
  4. 2023Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognitioncited by 23
  5. 2024Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformercited by 15
  6. 2023InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognitioncited by 11
  7. 2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
  8. 2024FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformercited by 10
  9. 2024Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognitioncited by 9
  10. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  11. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  12. 2024Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognitioncited by 5
19 more
  1. 2024Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognitioncited by 4
  2. 2025Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognitioncited by 4
  3. 2023A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognitioncited by 3
  4. 2024CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognitioncited by 3
  5. 2026Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognitioncited by 2
  6. 2023Deep Neural Networks in Video Human Action Recognition: A Reviewcited by 1
  7. 2023SkeleTR: Towrads Skeleton-based Action Recognition in the Wildcited by 1
  8. 2024SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorderscited by 1
  9. 2025Learning Adaptive Node Selection with External Attention for Human Interaction Recognitioncited by 1
  10. 2025THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footagecited by 0
  11. 2025G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 0
  12. 2025TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognitioncited by 0
  13. 20253D Human-Human Interaction Anomaly Detectioncited by 0
  14. 2026BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognitioncited by 0
  15. 2026STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognitioncited by 0
  16. 2026Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoningcited by 0
  17. 2026Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysiscited by 0
  18. 2026One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learningcited by 0
  19. 2026De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shiftcited by 0