Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition

29 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): “[193] Skeletal Quad Conc Lowlv Hand X X X Azary and Savakis [194] Grassmann Manifolds Conc Manif Hand X X X X Barnachon et al.”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, background): “Despite of the fact that the MSR Action3D dataset is made up of 567 sequences, the number of instances used in some works is unclear [18,19,20].”
A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, background): “The group of 8 activities labeled as Actions in the KARD [51] 72.9 Azary and Savakis (2013) [52] 78.5 Proposed (𝑃 = 7) 81.2 Azary and Savakis (2012) [50] 83.9 Chaaraoui et al. (2013) [15] 90.”
Accurate 3D action recognition using learning on the Grassmann manifold (2015, background): “Azary et al. [48] use a Grassmannian representation as an interpretation of depth motion image (DMI) computed from depth pixel values.”