Spatial-temporal pyramid based Convolutional Neural Network for action recognition

This letter presents a novel three-stream network for action recognition in extreme low resolution (LR) videos. In contrast to the existing networks, the new network uses the trajectory-spatial network, which is robust against visual distortion, instead of the pose information to complement the two-stream network. Also, the new three-stream network is combined with the inflated 3D ConvNet (I3D) model pre-trained on kinetics to produce more discriminative spatio-temporal features in blurred LR videos. Moreover, a bidirectional self-attention network is aggregated with the three-stream network to further manifest various temporal dependence among the spatio-temporal features. A new fusion strategy is devised as well to integrate the information from the three different modalities. Simulations show that the new architecture outperforms the main state-of-the-art extreme LR action recognition methods on the HMDB-51 and IXMAS datasets.

Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos

https://hal.archives-ouvertes.fr/hal-01580527/document

Class-balanced siamese neural networks

In order to overcome the problems of low accuracy and time-consuming of traditional prediction methods for short-term traffic flow in urban, a prediction methods for short-term traffic flow in urban based on multiple linear regression model is proposed. The corresponding data attributes of short-term traffic flow in urban are selected by traffic operation status, and used as the original data of traffic flow prediction. According to the selected attributes, spatial static attributes data and traffic flow dynamic attributes data are collected, and fault data are identified and repaired. A multiple linear regression model for prediction of short-term traffic flow in urban is constructed to realize the prediction of short-term traffic flow in urban. The experimental results show that, compared with other methods, the average prediction accuracy of the proposed method is as high as 98.48%, and the prediction time is always less than 0.7 s, which is shorter.

Predicting short-term traffic flow in urban based on multivariate linear regression model

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is...

https://onlinelibrary.wiley.com/doi/pdf/10.4218/etrij.2018-0102

Yufang Li

Papers

Region-based Mixture Models for human action recognition in low-resolution videos

A unified GCNN model for predicting CYP450 inhibitors by using graph convolutional neural networks with attention mechanism