Category-Blind Human Action Recognition: A Practical Recognition System

74 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, neutral): “9% CHARM [89] Geometric 83.”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, methodology): “For all datasets, the clips are generated with all frames of the original skeleton sequence without any pre-processing such as normalization, temporal down-sampling or noise ﬁl-tering.”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, neutral): “[59] 80.3% Ji et al., [63] 86.9% CHARM [64] 83.9% HBRNN [30] (reported by [51]) 80.4% Co-occurrence LSTM [51] 90.4% Deep LSTM (reported by [51]) 86.0% ST-LSTM (Joint Chain) 84.7% ST-LSTM (Tree) 88.6% ST-LSTM (Tree) + Trust Gate 93.3% Table 3.”
Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks (2018, unknown): “[46], Du et al.”
Adaptive RNN Tree for Large-Scale Human Action Recognition (2017, unknown): “CHARM [14] 0.”
Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, unknown): “3% CHARM [24] 83.”
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature (2016, methodology): “Please refer to [3,10,11,16] for details about DN search and its advantages over the GMCP [9,17] as a data association method.”