mlsanityData to 7 Oct 2026

Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives

arXiv 2307.13541 ↗First posted 25 Jul 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Group activity recognition is a hot topic in computer vision. Recognizing activities through group relationships plays a vital role in group activity recognition. It holds practical implications in various scenarios, such as video analysis, surveillance, automatic driving, and understanding social activities. The model's key capabilities encompass efficiently modeling hierarchical relationships within a scene and accurately extracting distinctive spatiotemporal features from groups. Given this technology's extensive applicability, identifying group activities has garnered significant research attention. This work examines the current progress in technology for recognizing group activities, with a specific focus on global interactivity and activities. Firstly, we comprehensively review the pertinent literature and various group activity recognition approaches, from traditional methodologies to the latest methods based on spatial structure, descriptors, non-deep learning, hierarchical recurrent neural networks (HRNN), relationship models, and attention mechanisms. Subsequently, we present the relational network and relational architectures for each module. Thirdly, we investigate methods for recognizing group activity and compare their performance with state-of-the-art technologies. We summarize the existing challenges and provide comprehensive guidance for newcomers to understand group activity recognition. Furthermore, we review emerging perspectives in group activity recognition to explore new directions and possibilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 128 references that are in the map. First posted on arXiv 25 Jul 2023.

Builds on

48 of 128 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2018SlowFast Networks for Video Recognitioncited by 1,862
  9. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  10. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  11. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  12. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
36 more
  1. 2017A simple neural network module for relational reasoningcited by 345
  2. 2018A Short Note about Kinetics-600cited by 331
  3. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  4. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 248
  5. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  6. 2020Human Action Recognition from Various Data Modalities: A Reviewcited by 162
  7. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  8. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  9. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  10. 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
  11. 2020Actor-Transformers for Group Activity Recognitioncited by 84
  12. 2019Learning Actor Relation Graphs for Group Activity Recognitioncited by 83
  13. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 82
  14. 2022Video Transformers: A Surveycited by 63
  15. 2016Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognitioncited by 43
  16. 2020Social Adaptive Module for Weakly-supervised Group Activity Recognitioncited by 42
  17. 2020Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videoscited by 39
  18. 2021Trear: Transformer-based RGB-D Egocentric Action Recognitioncited by 39
  19. 2019Convolutional Relational Machine for Group Activity Recognitioncited by 34
  20. 2017A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimationcited by 29
  21. 2019Progressive Relation Learning for Group Activity Recognitioncited by 28
  22. 2014Histogram of Oriented Principal Components for Cross-View Action Recognitioncited by 27
  23. 2015Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognitioncited by 27
  24. 2019Relational Action Forecastingcited by 27
  25. 2019Interaction Relational Network for Mutual Action Recognitioncited by 27
  26. 2022Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognitioncited by 27
  27. 2015Detecting events and key actors in multi-person videoscited by 26
  28. 2017CERN: Confidence-Energy Recurrent Network for Group Activity Recognitioncited by 24
  29. 2015Crowded Scene Analysis: A Surveycited by 21
  30. 2020Skeleton-based Relational Reasoning for Group Activity Analysiscited by 18
  31. 2021Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognitioncited by 12
  32. 20183D Human Pose Estimation with Relational Networkscited by 10
  33. 2015Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernelcited by 7
  34. 2019Ontology Based Global and Collective Motion Patterns for Event Classification in Basketball Videoscited by 4
  35. 2018Multi-Level Sequence GAN for Group Activity Recognitioncited by 3
  36. 2015Deep Structured Models For Group Activity Recognitioncited by 1

Built on by

Not cited yet.