mlsanityData to 7 Oct 2026

Continuous Human Action Recognition for Human-Machine Interaction: A Review

arXiv 2202.13096 ↗First posted 26 Feb 2022cs.CV cs.HC cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions within an input video are challenging but necessary tasks for applications that require real-time human-machine interaction. By reviewing a large body of recent related work in the literature, we thoroughly analyse, explain and compare action segmentation methods and provide details on the feature extraction and learning strategies that are used on most state-of-the-art methods. We cover the impact of the performance of object detection and tracking techniques on human action segmentation methodologies. We investigate the application of such models to real-world scenarios and discuss several limitations and key research directions towards improving interpretability, generalisation, optimisation and deployment.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 134 of its 198 references that are in the map. First posted on arXiv 26 Feb 2022.

Builds on

134 of 198 references.

References · 134

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
38 more
  1. 2014Going Deeper with Convolutionscited by 4,231
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2015Fast R-CNNcited by 2,930
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2014Conditional Generative Adversarial Netscited by 2,152
  13. 2017The Kinetics Human Action Video Datasetcited by 1,894
  14. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  15. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  16. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  17. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  18. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  19. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  20. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  21. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  22. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  23. 2019Objects as Pointscited by 1,172
  24. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  25. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  26. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  27. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  28. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  29. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  30. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  31. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  32. 2016Simple Online and Realtime Trackingcited by 862
  33. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  34. 2018Path Aggregation Network for Instance Segmentationcited by 796
  35. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  36. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  37. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  38. 2018Deep Visual Domain Adaptation: A Surveycited by 634

50 most cited of 134 All 134 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 3; 2025: 2; 2026: 3.

10 papers.

  1. 2024A Survey on Multimodal Wearable Sensor-based Human Action Recognitioncited by 10
  2. 2022Vision-Based Activity Recognition in Children with Autism-Related Behaviorscited by 7
  3. 2023Deep Learning Approaches for Seizure Video Analysis: A Reviewcited by 6
  4. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  5. 2024An Animation-based Augmentation Approach for Action Recognition from Discontinuous Videocited by 2
  6. 2024ContextDet: Temporal Action Detection with Adaptive Context Aggregationcited by 2
  7. 2025Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysiscited by 2
  8. 2026On the Evaluation Protocol of Gesture Recognition for UAV-based Rescue Operation based on Deep Learning: A Subject-Independence Perspectivecited by 1
  9. 2026SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognitioncited by 1
  10. 2026Can Large Language Models Detect Methodological Flaws? Evidence from Gesture Recognition for UAV-Based Rescue Operation Based on Deep Learningcited by 0