Hierarchical Bayesian Multiple Kernel Learning Based Feature Fusion for Action Recognition

2017 ◽  
pp. 85-97
Author(s):  
Wen Sun ◽  
Chunfeng Yuan ◽  
Pei Wang ◽  
Shuang Yang ◽  
Weiming Hu ◽  
...  
Keyword(s):  
Action Recognition ◽  
Feature Fusion ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Hierarchical Bayesian ◽  
Multiple Kernel

Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos

2011 ◽  
Vol 21 (9) ◽  
pp. 1193-1202 ◽  
Author(s):  
Yan Song ◽  
Yan-Tao Zheng ◽  
Sheng Tang ◽  
Xiangdong Zhou ◽  
Yongdong Zhang ◽  
...  
Keyword(s):  
Action Recognition ◽  
Multiple Kernel Learning ◽  
Human Action Recognition ◽  
Human Action ◽  
Kernel Learning ◽  
Multiple Kernel

scholarly journals A Novel Multiple Kernel Learning Framework for Heterogeneous Feature Fusion and Variable Selection

2012 ◽  
Vol 14 (3) ◽  
pp. 563-574 ◽  
Author(s):  
Yi-Ren Yeh ◽  
Ting-Chu Lin ◽  
Yung-Yu Chung ◽  
Yu-Chiang Frank Wang
Keyword(s):  
Variable Selection ◽  
Feature Fusion ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Learning Framework ◽  
Multiple Kernel ◽  
Heterogeneous Feature

Multi-Channel MKL for Video Human Action Recognition

2014 ◽  
Vol 599-601 ◽  
pp. 1571-1574
Author(s):  
Jia Ding ◽  
Yang Yi ◽  
Ze Min Qiu ◽  
Jun Shi Liu
Keyword(s):  
Action Recognition ◽  
Recognition Rate ◽  
Multiple Kernel Learning ◽  
Human Action Recognition ◽  
Human Action ◽  
Image Understanding ◽  
Kernel Learning ◽  
Bag Of Visual Words ◽  
Visual Words ◽  
Multiple Kernel

Human action recognition in videos plays an important role in the field of computer vision and image understanding. A novel method of multi-channel bag of visual words and multiple kernel learning is proposed in this paper. The videos are described by multi-channel bag of visual words, and a multiple kernel learning classifier is used for action classification, in which each kernel function of the classifier corresponds to a video channel in order to avoid the noise interference from other channels. The proposed approach improves the ability in distinguishing easily confused actions. Experiments on KTH show that the presented method achieves remarkable performance on the average recognition rate, and obtains comparable recognition rate with state-of-the-art methods.

Multilayer deep features with multiple kernel learning for action recognition

2020 ◽  
Vol 399 ◽  
pp. 65-74
Author(s):  
Biyun Sheng ◽  
Jun Li ◽  
Fu Xiao ◽  
Wankou Yang
Keyword(s):  
Action Recognition ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Multiple Kernel
Sign in / Sign up

Export Citation Format

Share Document