# Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph

arXiv: https://arxiv.org/abs/2407.19497 · HTML: https://mlsanity.com/paper/2407.19497/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 76 references that are in the map.
- First posted on arXiv 28 Jul 2024.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition](https://mlsanity.com/paper/2010.09978/) (2020)
- [Hierarchical Deep Temporal Models for Group Activity Recognition](https://mlsanity.com/paper/1607.02643/) (2016)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.10741/) (2022)
- [Actor-Transformers for Group Activity Recognition](https://mlsanity.com/paper/2003.12737/) (2020)
- [Learning Actor Relation Graphs for Group Activity Recognition](https://mlsanity.com/paper/1904.10117/) (2019)
- [GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer](https://mlsanity.com/paper/2108.12630/) (2021)
- [Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning](https://mlsanity.com/paper/2212.03229/) (2022)
- [Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition](https://mlsanity.com/paper/1611.09078/) (2016)
- [Social Adaptive Module for Weakly-supervised Group Activity Recognition](https://mlsanity.com/paper/2007.09470/) (2020)
- [Spatio-Temporal Dynamic Inference Network for Group Activity Recognition](https://mlsanity.com/paper/2108.11743/) (2021)
- [Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos](https://mlsanity.com/paper/2007.02632/) (2020)
- [Convolutional Relational Machine for Group Activity Recognition](https://mlsanity.com/paper/1904.03308/) (2019)
- [On the Benefits of 3D Pose and Tracking for Human Action Recognition](https://mlsanity.com/paper/2304.01199/) (2023)

## Built on by (most cited first, 6 of 6)

- [SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic](https://mlsanity.com/paper/2503.06522/) (2025)
- [Pixels or Positions? Benchmarking Modalities in Group Activity Recognition](https://mlsanity.com/paper/2511.12606/) (2025)
- [PromptGAR: Flexible Promptive Group Activity Recognition](https://mlsanity.com/paper/2503.08933/) (2025)
- [Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval](https://mlsanity.com/paper/2602.03157/) (2026)
- [Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning](https://mlsanity.com/paper/2604.04467/) (2026)
- [Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach](https://mlsanity.com/paper/2607.00716/) (2026)

## Abstract (arXiv)

Group Activity Recognition aims to understand collective activities from videos. Existing solutions primarily rely on the RGB modality, which encounters challenges such as background variations, occlusions, motion blurs, and significant computational overhead. Meanwhile, current keypoint-based methods offer a lightweight and informative representation of human motions but necessitate accurate individual annotations and specialized interaction reasoning modules. To address these limitations, we design a panoramic graph that incorporates multi-person skeletons and objects to encapsulate group activity, offering an effective alternative to RGB video. This panoramic graph enables Graph Convolutional Network (GCN) to unify intra-person, inter-person, and person-object interactive modeling through spatial-temporal graph convolutions. In practice, we develop a novel pipeline that extracts skeleton coordinates using pose estimation and tracking algorithms and employ Multi-person Panoramic GCN (MP-GCN) to predict group activities. Extensive experiments on Volleyball and NBA datasets demonstrate that the MP-GCN achieves state-of-the-art performance in both accuracy and efficiency. Notably, our method outperforms RGB-based approaches by using only estimated 2D keypoints as input. Code is available at https://github.com/mgiant/MP-GCN