View-Invariant Action Recognition Based on Artificial Neural Networks

143 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.

View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data (2017, background): “One category of approaches requires multiple view videos for training [15, 8, 41, 44, 25].”
View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, background): “Some attempts have been made in previous works to overcome the view variation problem for robust action recognition [3], [8], [9], [14], [15], [19], [24], [26], [31], [36], [37], [39], [40], [50], [52], [53], [60].”
Discriminant Bag of Words based representation for human action recognition (2014, methodology): “…to fuse the information coming from all available cameras, the action videos depicting the same test action instance from different viewing angles have been classiﬁed independently and the obtained action class labels were fused by using a simple majority voting fusion scheme, similar to ([15]).”
A Review of Human Activity Recognition Methods (2015, methodology): “Self organizingmaps (SOM) (Kohonen et al., 2001) were introduced by Iosifidis et al. (2012b) for learning humanbody posture, in conjunction with fuzzy distances, to achieve time invariant action representation.”
Minimum Variance Extreme Learning Machine for human action recognition (2014, methodology): “In the case of ELM-based classification, multiple descriptors are combined by using the network output sum [18, 19]:”