Human Motion Retrieval Based on Feedback Learning

2017 ◽  
Author(s):  
Qinkun Xiao ◽  
Yidan Zhao ◽  
Kin Fun Li
Keyword(s):  
Human Motion ◽  
Feedback Learning ◽  
Motion Retrieval

Relevance feedback for human motion retrieval using a boosting approach

2014 ◽  
Vol 75 (2) ◽  
pp. 787-817 ◽  
Author(s):  
Songle Chen ◽  
Zhengxing Sun ◽  
Yan Zhang ◽  
Qian Li
Keyword(s):  
Relevance Feedback ◽  
Human Motion ◽  
Motion Retrieval

Human motion retrieval using topic model

2011 ◽  
Vol 23 (5) ◽  
pp. 469-476 ◽  
Author(s):  
Mingyang Zhu ◽  
Huaijiang Sun ◽  
Rongyi Lan ◽  
Bin Li
Keyword(s):  
Topic Model ◽  
Human Motion ◽  
Motion Retrieval

scholarly journals An Efficient Dynamic Regulated Fuzzy Neural Network for Human Motion Retrieval and Analysis

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1317
Author(s):  
Xin Huang ◽  
Yuanping Zhu ◽  
Shuqin Wang
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Learning Algorithm ◽  
Human Action ◽  
Human Motion ◽  
Estimation Accuracy ◽  
Human Motion Analysis ◽  
Critical Feature ◽  
Fuzzy Neural ◽  
Motion Retrieval

Human motion retrieval and analysis is a useful means of activity recognition to 3D human bodies. An efficient method is proposed to estimate human motion by using symmetric joint points and limb features of various limb parts based on regression task. We primarily obtain the 3D coordinates of symmetric joint points based on the located waist and hip points. By introducing three critical feature points on torso and symmetric joint points’ matching on motion video sequences, the 3D coordinates of symmetric joint points and its asymmetric limb features will not be affected by shading and interference of limb on different postures. With the asymmetric limb features of various human parts, a dynamic regulated Fuzzy neural network (DRFNN) is proposed to estimate human motion for different asymmetric postures using learning algorithm of network parameters and weights. Finally, human sequential actions corresponding to different asymmetric postures are presented according to the best retrieval results by DRFNN based on 3D human action database. Experiments show that compared with the traditional adaptive self-organizing fuzzy neural network (SOFNN) model, the proposed algorithm has higher estimation accuracy and better presentation results compared with the existing human motion analysis algorithms.

Spatial temporal pyramid matching using temporal sparse representation for human motion retrieval

2014 ◽  
Vol 30 (6-8) ◽  
pp. 845-854 ◽  
Author(s):  
Liuyang Zhou ◽  
Zhiwu Lu ◽  
Howard Leung ◽  
Lifeng Shang
Keyword(s):  
Sparse Representation ◽  
Human Motion ◽  
Motion Retrieval ◽  
Pyramid Matching

A Novel Retrieval Method Based on Semantic Motion

2012 ◽  
Vol 468-471 ◽  
pp. 103-106 ◽  
Author(s):  
Jian Xiang
Keyword(s):  
Motion Capture ◽  
Three Dimensional ◽  
Human Motion ◽  
Retrieval Algorithm ◽  
Widespread Application ◽  
Retrieval Method ◽  
Key Frame ◽  
Motion Data ◽  
Motion Retrieval ◽  
3D Retrieval

With the widespread application of motion capture technology, three-dimensional(3D) motion data can be directly obtained. In this paper, a new 3D retrieval algorithm based on semantic motion is proposed. With semantic motion template and extracting key-frame, 3D human motion database can be processed effectively by retrieval. Experiment results show that our method can improve the accuracy of motion retrieval.

Assessing similarity models for human-motion retrieval applications

2015 ◽  
Vol 27 (5) ◽  
pp. 484-500 ◽  
Author(s):  
Jakub Valcik ◽  
Jan Sedmidubsky ◽  
Pavel Zezula
Keyword(s):  
Human Motion ◽  
Motion Retrieval
Sign in / Sign up

Export Citation Format

Share Document