Eurographics/ Acm Siggraph Symposium on Computer Animation (2006) Motion Templates for Automatic Classification and Retrieval of Motion Capture Data

How researchers see this paper

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

Citations in the corpus

Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition (2014, methodology): “…more directly related to the underlying causes of the data than to the individual elements of the data itself (previous hardwired techniques [3, 20, 23, 24] have shown that multiple joints relational features, e.g. hands approaching each other, feet moving towards each other, etc., are more…”
Learning Maximum Margin Temporal Warping for Action Recognition (2013, methodology): “This is similar to dynamic temporal warping [14].”
Documentation Mocap Database HDM05 (2007, methodology): “…away from chair and turn around [9] walk 3 steps to table [10] sit down on table [11] stand up [12] walk 3 steps away from table and turn around [13] walk 3 steps to table [14] sit down on table [15] stand up [16] walk 3 steps away from table and turn around [17] walk 3 steps to lying position…”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, unknown): “In addition, our JOULE works better than MTDA on CAD 60 set with a smaller performance gain than on the MSR Daily set.”
Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data (2014, unknown): “Veeraraghavan and Roy-chowdhury [22] compute a nominal activity trajectory for each action category using DTW. Müller and Röder [23] use DTW for matching the 3D joint positions to a motion template.”
Action recognition using ensemble weighted multi-instance learning (2014, background): “[13] matched the 3D joint positions to the templates, and action recognition can be done through a nearest-neighbor classification method.”
Gesture Modeling by Hanklet-Based Hidden Markov Model (2014, methodology): “Methods [47]* [10]* [11]* [12] [24] [48]** [13]** [25] [23] [13]** Ours”
Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps (2013, background): “25% Dynamic Temporal Wrapping [14] 54% 3D Joints Fourier [19] 68% Actionlet Ensemble [19] 85.”
Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests (2012, methodology): “angles, [18], [19] and body joints [20], [21].”
Mining Mid-Level Features for Action Recognition Based on Effective Skeleton Representation (2014, background): “Methods Accuracy (%) Dynamic Temporal Warping [29] 54.”
The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection (2013, methodology): “5 Dynamic Temporal Warping [15] 54 Hidden Markov Model [12] 63 Latent-Dynamic CRF [14] 64.”
Joint Angles Similarities and HOG2 for Action Recognition (2013, unknown): “Since we are concerned with a multi-variate series modeling problem, dynamic temporal warping (DTW) can be employed to perform action recognition by template matching [12].”