Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking

34 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.

Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, background): “The body joints are popularly represented as a tree-based pictorial structure [64], [65] in human parsing, as shown in Fig.”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, background): “relations between the joints and adds false connections between body joints which are not strongly related. In human parsing, skeletal joints are popularly modeled as a tree-based pictorial structure [55,56], as illustrated in Fig. 2(b). In our ST-LSTM framework, it is also benecial to model the spa”
Skeleton-Based Action Recognition With Directed Graph Neural Networks (2019, unknown): “In human parsing, the skeleton data are always modeled as a tree-based pictorial structure [39, 35] according to the physical structure of the human body.”