Efficient Pose-Based Action Recognition

67 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[211] Discriminative Action Features Conc Lowlv Unsup X X X Guerra-Filho and Aloimonos [212] Visuo-motor Primitives Conc Lowlv Hand X X X”
Moving Poselets: A Discriminative and Interpretable Skeletal Motion Representation for Action Recognition (2015, unknown): “7 [6] 91.”
Category-Blind Human Action Recognition: A Practical Recognition System (2015, background): “However, existing algorithms designed to recognize single-person actions from sequences of 3D joint positions [10, 19, 25] cannot be used to recognize multi-person interactions, and vice versa [4, 23].”
3D skeleton-based human action classification: A survey (2016, methodology): “99%** M [124] NBNN – – 70% – – M [103] PLS-SVM – – 70% – 91.”
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold (2016, unknown): “22 - - - Pose2[12] 91.”
A Review of Human Activity Recognition Methods (2015, background): “Eweiwi et al. (2014) reduced the required amount of pose data using a fixed length vector of more informative motion features (e.g., location and velocity) for each skeletal point.”