Video-Based Human Motion Capture Data Retrieval via MotionSet Network

Ren, Tingxin; Wei, Li; Jiang, Zifei; Li, Xueqing; Huang, Yan; Peng, Jingliang

doi:10.1109/access.2020.3030258

Cited by 9 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assuming that the retrieval time of the data elements in each data bucket obtained from the division of Wushu teaching data is X, the calculation formula of the mathematical expected value E(X) B of the random variable is as follows [11,12]:…”

Section: Establishment Of Wushu Teaching Data Grid Indexmentioning

confidence: 99%

Evaluation Method of Wushu Teaching Quality Based on Fuzzy Clustering

Zhu

Wang

2022

Security and Communication Networks

View full text Add to dashboard Cite

The existing teaching quality evaluation methods cannot calculate the distance between the data points of teaching dataset and the center points of the large density grid, which leads to the poor classification of teaching data and the low accuracy of teaching quality evaluation. Therefore, a method of teaching quality evaluation of Wushu based on fuzzy clustering is proposed. In order to improve the comprehensiveness of teaching quality evaluation, the lost data of teaching resources were recovered. Based on this, the grid index of martial arts teaching data is established, and the relationship model between teaching quality and martial arts achievement is constructed. Based on the characteristics of Wushu teaching resources, the fuzzy clustering method is introduced to calculate the distance between each data point and the grid center with high data density. The experimental results show that the evaluation accuracy of the teaching quality is high, and the lost data can be accurately recovered. The evaluation efficiency, reliability, and stability of Wushu teaching quality are ideal.

show abstract

Section: Establishment Of Wushu Teaching Data Grid Indexmentioning

confidence: 99%

Evaluation Method of Wushu Teaching Quality Based on Fuzzy Clustering

Zhu

Wang

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…There are many ways to interpret and represent human motions, such as kinematic trees [56,30], joints graph [102,57], video frames [32,82], and moving as a mass point from a starting point to a target point, which all reflect people's ruili.wang@massey.ac.nz (R. Wang) ORCID(s): 0000-0002-7905-3759 (K. Lyu) 1 This is the first author footnote. different comprehensions of human motion, resulting in diverse manifestations of human motion prediction.…”

Section: Scopementioning

confidence: 99%

3D Human Motion Prediction: A Survey

Lyu¹,

Chen²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors. Due to the increasing development and understanding of Deep Neural Networks (DNNs) and the availability of large-scale human motion datasets, the human motion prediction has been remarkably advanced with a surge of interest among academia and industrial community. In this context, a comprehensive survey on 3D human motion prediction is conducted for the purpose of retrospecting and analyzing relevant works from existing released literature. In addition, a pertinent taxonomy is constructed to categorize these existing approaches for 3D human motion prediction. In this survey, relevant methods are categorized into three categories: human pose representation, network structure design, and prediction target. We systematically review all relevant journal and conference papers in the field of human motion prediction since 2015, which are presented in detail based on proposed categorizations in this survey. Furthermore, the outline for the public benchmark datasets, evaluation criteria, and performance comparisons are respectively presented in this paper. The limitations of the state-of-the-art methods are discussed as well, hoping for paving the way for future explorations.

show abstract

“…However, these two objectives-efficiency and effectiveness-are difficult to achieve at the same time. Many existing retrieval techniques [2,18,19,24] focus solely on search quality and do not discuss the efficiency at all, which leads to expensive sequential scan over the whole dataset. The efficiencyoriented works either propose very compact features that allow fast sequential scanning [12,13], or utilize various indexing schemes to organize the motion data (e.g., the binary tree [25], kd tree [9], R* tree [4], inverted file index [14], or tries [8]).…”

Section: Introductionmentioning

confidence: 99%

Efficient Indexing of 3D Human Motions

Budikova

Sedmidubský

Zezula

2021

Proceedings of the 2021 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Basic posting lists for dataset MWs MW matching indexFigure 1: Efficient skeleton-data retrieval. In a pre-processing phase, skeleton sequences are transformed into motion documents, i.e., compact text-like representations composed of structured motion words (MWs). The motion documents are organized using a new indexing scheme that extends the traditional inverted files. During query processing, candidate documents are efficiently retrieved by a proposed approximate search algorithm and finally re-ranked using the DTW alignment.

show abstract

Video-Based Human Motion Capture Data Retrieval via MotionSet Network

Cited by 9 publications

References 31 publications

Evaluation Method of Wushu Teaching Quality Based on Fuzzy Clustering

Evaluation Method of Wushu Teaching Quality Based on Fuzzy Clustering

3D Human Motion Prediction: A Survey

Efficient Indexing of 3D Human Motions

Contact Info

Product

Resources

About