In this paper, a novel approach via embedded tensor manifold regularizat...
Semantic segmentation methods can not directly identify abnormal objects...
The modeling, computational cost, and accuracy of traditional Spatio-tem...
Capsule neural network is a new and popular technique in deep learning.
...
Spatial and temporal features are two key and complementary information ...
Most existing Convolutional Neural Networks(CNNs) used for action recogn...