Corpus ID: 53101390

ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition

  title={ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition},
  author={Federico Angelini and Zeyu Fu and Yang Long and L. Shao and S. Naqvi},
We present ActionXPose, a novel 2D pose-based algorithm for posture-level Human Action Recognition (HAR. [...] Key Method The algorithm has real-time performance and it is robust to camera movings, subject proximity changes, viewpoint changes, subject appearance changes and provide high generalization degree. In fact, extensive simulations show that ActionXPose can be successfully trained using different datasets at once. State-of-the-art performance on popular datasets for posture-related HAR problems…Expand
9 Citations
Simple yet efficient real-time pose-based action recognition
  • 10
  • PDF
Joint RGB-Pose Based Human Action Recognition for Anomaly Detection Applications
  • 1
  • Highly Influenced
Deep Learning-Based Human Pose Estimation: A Survey
  • 27
  • PDF
Multi-scale affined-HOF and dimension selection for view-unconstrained action recognition
  • 1
Enhancing Data-Driven Algorithms for Human Pose Estimation and Action Recognition Through Simulation
  • 1
Privacy-preserving Online Human Behaviour Anomaly Detection Based on Body Movements and Objects Positions
  • 4
Quo Vadis, Skeleton Action Recognition ?
  • 2
  • PDF
Mimetics: Towards Understanding Human Actions Out of Context
  • 9
  • PDF


3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes
  • 9
  • PDF
3D Convolutional Neural Networks for Human Action Recognition
  • 3,514
  • PDF
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction
  • 182
  • PDF
Actions as Space-Time Shapes
  • 1,510
  • Highly Influential
  • PDF
Hierarchical Hough forests for view-independent action recognition
  • 6
  • PDF
A Survey on Human Action Recognition Using Depth Sensors
  • Bin Liang, Lihong Zheng
  • Computer Science
  • 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
  • 2015
  • 32
Two-Stream Convolutional Networks for Action Recognition in Videos
  • 4,486
  • PDF
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
  • 2,887
  • Highly Influential
  • PDF
The i3DPost Multi-View and 3D Human Action/Interaction Database
  • 168
  • PDF