Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN

2017 ◽  
Author(s):  
Bo Li ◽  
Yuchao Dai ◽  
Xuelian Cheng ◽  
Huahui Chen ◽  
Yi Lin ◽  
...  
Keyword(s):  
Action Recognition ◽  
Scale Invariant ◽  
Multi Scale ◽  
Image Mapping ◽  
Deep Cnn

3D skeleton based action recognition by video-domain translation-scale invariant mapping and multi-scale dilated CNN

2018 ◽  
Vol 77 (17) ◽  
pp. 22901-22921 ◽  
Author(s):  
Bo Li ◽  
Mingyi He ◽  
Yuchao Dai ◽  
Xuelian Cheng ◽  
Yucheng Chen
Keyword(s):  
Action Recognition ◽  
Scale Invariant ◽  
Multi Scale ◽  
3D Skeleton

Skeleton-based Action Recognition with Multi-scale Spatial-temporal Convolutional Neural Network

2021 ◽  
Author(s):  
Qin Cheng ◽  
Ziliang Ren ◽  
Jun Cheng ◽  
Qieshi Zhang ◽  
Hao Yan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Action Recognition ◽  
Multi Scale

scholarly journals Multi-scale invariant fields: estimation and prediction

2020 ◽  
Vol 2020 (7) ◽  
pp. 073408
Author(s):  
H Ghasemi ◽  
S Rezakhah ◽  
N Modarresi
Keyword(s):  
Scale Invariant ◽  
Multi Scale ◽  
Estimation And Prediction

A Tracking Window Adaptive Compressive Tracking Algorithm

2019 ◽  
Vol 33 (14) ◽  
pp. 1959045 ◽  
Author(s):  
Wenhao Wang ◽  
Mingxin Jiang ◽  
Xiaobing Chen ◽  
Li Hua ◽  
Shangbing Gao
Keyword(s):  
Texture Features ◽  
Candidate Region ◽  
Tracking Algorithm ◽  
Experimental Results ◽  
Scale Invariant ◽  
Compressive Tracking ◽  
Multi Scale ◽  
Feature Normalization ◽  
Object Region ◽  
Candidate Regions

In the original compression tracking algorithm, the size of the tracking box is fixed. There should be better tracking results for scale-invariant objects, but worse tracking results for scale-variant objects. To overcome this defect, a scale-adaptive compressive tracking (CT) algorithm is proposed. First of all, the imbalance of the gray and texture features in the original CT algorithm is balanced by the multi-feature method, which makes the algorithm more robust. Then, searching different candidate regions by using the method of multi-scale search along with feature normalization makes the features extracted from different scales comparable. Finally, the candidate region with the maximum discriminate degree is selected as the object region. Thus, the tracking-box size is adaptive. The experimental results show that when the object scale changes, the improving CT algorithm has higher accuracy and robustness than the original CT algorithm.

Sign in / Sign up

Export Citation Format

Share Document