Data to 7 Oct 2026

Spatial Temporal Transformer Network for Skeleton-based Action Recognition

arXiv 2012.06399 ↗First posted 11 Dec 2020cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an effective encoding of the latent information underlying the 3D skeleton is still an open problem. In this work, we propose a novel Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using the Transformer self-attention operator. In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations. The two are combined in a two-stream network which outperforms state-of-the-art models using the same input data on both NTU-RGB+D 60 and NTU-RGB+D 120.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 24; 2023: 18; 2024: 12; 2025: 13.

76 papers.

Sort:

By area:

2021Transformers in Vision: A Surveycited by 1,009
2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43
2022Delving into Sequential Patches for Deepfake Detectioncited by 41
2022CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Predictioncited by 39
2023GPGait: Generalized Pose-based Gait Recognitioncited by 39
2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
2022Global-local Motion Transformer for Unsupervised Skeleton-based Action Learningcited by 33
2022Spatial Transformer Network on Skeleton-based Gait Recognitioncited by 32
2022DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognitioncited by 31
2022Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learningcited by 30

38 more

2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
2022TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibrationcited by 25
2022Vision Transformers for Action Recognition: A Surveycited by 25
2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
2022Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformerscited by 18
2022GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixercited by 18
2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
2024On the Utility of 3D Hand Poses for Action Recognitioncited by 17
2022Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusionscited by 13
2024Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videoscited by 13
2021Hierarchical Graph Convolutional Skeleton Transformer for Action Recognitioncited by 12
2022Multimodal Transformer for Nursing Activity Recognitioncited by 12
2023Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognitioncited by 11
2023GaitPT: Skeletons Are All You Need For Gait Recognitioncited by 11
2024CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Mannercited by 11
2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
2022FAR: Fourier Aerial Video Recognitioncited by 10
2022Unsupervised Domain Adaptation for Video Transformers in Action Recognitioncited by 10
2024Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignmentcited by 10
2021Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognitioncited by 9
2021NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecastingcited by 8
2021STAR: Sparse Transformer-based Action Recognitioncited by 8
2023Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awarenesscited by 8
2023Human Part-wise 3D Motion Context Learning for Sign Language Recognitioncited by 8
2023GaitContour: Efficient Gait Recognition based on a Contour-Pose Representationcited by 8
2023GaitFormer: Learning Gait Representations with Noisy Multi-Task Learningcited by 7
2021Robust Event Detection based on Spatio-Temporal Latent Action Unit using Skeletal Informationcited by 6
2022Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillancecited by 6
2022A Light Touch Approach to Teaching Transformers Multi-view Geometrycited by 6
2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
2023Large Scale Foundation Models for Intelligent Manufacturing Applications: A Surveycited by 6
2024Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inferencecited by 6
2022Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Modelcited by 5
2023Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosiscited by 5
2025Towards Robust and Realistic Human Pose Estimation via WiFi Signalscited by 5
2022Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognitioncited by 4
2023Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phasecited by 4
2024Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognitioncited by 4

50 most cited of 76 All 76 (JSON)