An Action Recognition network for specific target based on rMC and RPN

06/19/2019
by   Mingjie Li, et al.
3

The traditional methods of action recognition are not specific for the operator, thus results are easy to be disturbed when other actions are operated in videos. The network based on mixed convolutional resnet and RPN is proposed in this paper. The rMC is tested in the data set of UCF-101 to compare with the method of R3D. The result shows that its correct rate reaches 71.07 Meanwhile, the action recognition network is tested in our gesture and body posture data sets for specific target. The simulation achieves a good performance in which the running speed reaches 200 FPS. Finally, our model is improved by introducing the regression block and performs better, which shows the great potential of this model.

READ FULL TEXT

page 6

page 7

page 8

page 9

research
05/08/2017

Temporal Segment Networks for Action Recognition in Videos

Deep convolutional networks have achieved great success for image recogn...
research
08/02/2016

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

Deep convolutional networks have achieved great success for visual recog...
research
03/21/2018

T-RECS: Training for Rate-Invariant Embeddings by Controlling Speed for Action Recognition

An action should remain identifiable when modifying its speed: consider ...
research
08/03/2021

Classifying action correctness in physical rehabilitation exercises

The work in this paper focuses on the role of machine learning in assess...
research
07/31/2015

Multimodal Multipart Learning for Action Recognition in Depth Videos

The articulated and complex nature of human actions makes the task of ac...

Please sign up or login with your details

Forgot password? Click here to reset