Linear-time online action detection from 3D skeletal data using bags of gesturelets

31 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, methodology): “[209] Angle & Moving Pose BoW Lowlv Unsup X X X X”
Real-Time Online Action Detection Forests Using Spatio-Temporal Contexts (2016, methodology): “his objective, the consistency between mean of two groups and individual sample is considered based on context space Z (Green circle). Method mean AP Time per Frame Moving Pose [47] 0.890±0.002 − ELS [23] 0.902±0.007 9.1 ms RF 0.820±0.015 RF+T 0.885±0.012 1.1 ms RF+ST 0.920±0.008 Table 1. Comparison”
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, background): “A similar approach but adding multi-scale information was proposed by [20], while [17] proposed a dynamic bag of features.”