mlsanityData to 7 Oct 2026

Panoramic Human Activity Recognition

arXiv 2203.03806 ↗First posted 8 Mar 2022cs.CV cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simultaneous achieve the individual action, social group activity, and global activity recognition. This is a challenging yet practical problem in real-world applications. For this problem, we develop a novel hierarchical graph neural network to progressively represent and model the multi-granularity human activities and mutual social relations for a crowd of people. We further build a benchmark to evaluate the proposed method and other existing related methods. Experimental results verify the rationality of the proposed PAR problem, the effectiveness of our method and the usefulness of the benchmark. We will release the source code and benchmark to the public for promoting the study on this problem.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 25 of its 57 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

25 of 57 references.

References · 25

  1. 2017Mask R-CNNcited by 7,259
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2018SlowFast Networks for Video Recognitioncited by 1,862
  4. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  5. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  6. 2020Actor-Context-Actor Relation Network for Spatio-Temporal Action Localizationcited by 91
  7. 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
  8. 2020Actor-Transformers for Group Activity Recognitioncited by 84
  9. 2019Learning Actor Relation Graphs for Group Activity Recognitioncited by 83
  10. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 82
  11. 2020Asynchronous Interaction Aggregation for Action Detectioncited by 65
  12. 2020SF-Net: Single-Frame Supervision for Temporal Action Localizationcited by 62
13 more
  1. 2018Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learningcited by 47
  2. 2020PANDA: A Gigapixel-level Human-centric Video Datasetcited by 45
  3. 2016Deep Learning on Lie Groups for Skeleton-based Action Recognitioncited by 42
  4. 2020Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videoscited by 39
  5. 2018Spatio-Temporal Channel Correlation Networks for Action Classificationcited by 38
  6. 2021JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detectioncited by 38
  7. 2020Context-Aware RCNN: A Baseline for Action Detection in Videoscited by 33
  8. 2017CERN: Confidence-Energy Recurrent Network for Group Activity Recognitioncited by 24
  9. 2018Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognitioncited by 20
  10. 2016Spot On: Action Localization from Pointly-Supervised Proposalscited by 17
  11. 2018GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowdscited by 15
  12. 2016Human Action Localization with Sparse Spatial Supervisioncited by 8
  13. 2018Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classificationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 4; 2025: 4.

13 papers.

Sort:

  1. 2025Omnidirectional Multi-Object Trackingcited by 12
  2. 2023Towards More Practical Group Activity Detection: A New Benchmark and Modelcited by 11
  3. 2023SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognitioncited by 8
  4. 2023REACT: Recognize Every Action Everywhere All At Oncecited by 5
  5. 2023Real-time Trajectory-based Social Group Detectioncited by 4
  6. 2025Dynamic Group Detection using VLM-augmented Temporal Groupness Graphcited by 3
  7. 2023Boundary Discretization and Reliable Classification Network for Temporal Action Detectioncited by 2
  8. 2025OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedbackcited by 2
  9. 2024Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognitioncited by 1
  10. 2024LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognitioncited by 1
  11. 2025Structured Relational Reasoning for Group Activity Assessmentcited by 1
  12. 2024Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learningcited by 0
1 more
  1. 2024MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognitioncited by 0