The Experts below are selected from a list of 2658 Experts worldwide ranked by ideXlab platform
Yu-gang Jiang - One of the best experts on this subject based on the ideXlab platform.
-
Learning to score the Figure Skating sports videos
arXiv: Multimedia, 2018Co-Authors: Fu Yanwei, Zitian Chen, Yu-gang Jiang, Bing Zhang, Xiangyang XueAbstract:This paper targets at learning to score the Figure Skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale Figure Skating sports video dataset -- FisV dataset. This dataset includes 500 Figure Skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the Figure Skating videos.
-
Learning to Score Figure Skating Sport Videos
IEEE Transactions on Circuits and Systems for Video Technology, 1Co-Authors: Chengming Xu, Yanwei Fu, Zitian Chen, Bing Zhang, Yu-gang JiangAbstract:This paper aims at learning to score the Figure Skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale Figure Skating sports video dataset FisV dataset. This dataset includes 500 Figure Skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the Figure Skating videos. The codes and datasets would be downloaded from https://github.com/loadder/MS_LSTM.git.
Sarah T. Ridge - One of the best experts on this subject based on the ideXlab platform.
-
icesense proof of concept calibrating an instrumented Figure Skating blade to measure on ice forces
Sensors, 2020Co-Authors: Sarah T. Ridge, Dustin A. Bruening, Riley E. Reynolds, Chris Adair, Daniel Michael Smith, Steven K Charles, Cody Stahl, Brandon Adamo, Blake Harper, Preston K ManwaringAbstract:Competitive Figure skaters often suffer from overuse injuries, which may be due to the high impact forces endured during jump repetitions performed in practice and competition. However, to date, forces during on-ice Figure Skating have not been quantified due to technological limitations. The purpose of this study was to determine the optimal calibration procedure for a previously developed instrumented Figure Skating blade (IceSense). Initial calibration was performed by collecting data from the blade while 11 skaters performed off-ice jumps, landing on a force plate in the lab. However, mean peak force measurements from the blade were greater than the desired error threshold of ±10%. Therefore, we designed a series of controlled experiments which included measuring forces from a load cell rigidly attached to the top of the blade concurrently with strain data from the strain gauges on the blade. Forces were applied to the blade by adding weight to a drop tower or by manually applying force in a quasi-static manner. Both methods showed similar accuracy, though using the drop tower allowed precise standardization. Therefore, calibration was performed using the weighted drop method. This calibration was applied to strain gauge data from out-of-sample drop trials, resulting in acceptable estimates of peak force (less than 10% error). Using this calibration, we collected data on one Figure skater and present results from an exemplar on-ice double flip jump. Using the IceSense device to quantify on-ice forces in a research setting may help inform training, technique, and equipment design.
-
A Sport-Specific Wearable Jump Monitor for Figure Skating
PloS one, 2018Co-Authors: Dustin A. Bruening, Riley E. Reynolds, Chris Adair, Peter Zapalo, Sarah T. RidgeAbstract:Advancements in wearable technology have facilitated performance monitoring in a number of sports. Figure Skating may also benefit from this technology, but the inherent movements present some unique challenges. The purpose of this study was to evaluate the feasibility of using an inertial measurement unit (IMU) to monitor three aspects of Figure Skating jumping performance: jump count, jump height, and rotation speed. Seven competitive Figure skaters, outfitted with a waist-mounted IMU, performed a total of 59 isolated multi-revolution jumps and their competition routines, which consisted of 41 multi-revolution jumps along with spins, footwork, and other skills. The isolated jumps were used to develop a jump identification algorithm, which was tested on the competition routines. Four algorithms to estimate jump height from flight time were then evaluated using calibrated video as a gold standard. The identification algorithm counted 39 of the 41 program jumps correctly, with one false positive. Flight time and jump height errors under 7% and 15% respectively were found using a peak-to-peak scaling algorithm. Rotation speeds up to 1,500°/s were noted, with peak speeds occurring just over halfway between takeoff and landing. Overall, jump monitoring via IMUs may be an efficient aid for Figure skaters training multi-revolution jumps.
-
instrumented Figure Skating blade for measuring on ice Skating forces
Measurement Science and Technology, 2014Co-Authors: Samuel A Acuna, Deborah L. King, Sarah T. Ridge, Daniel Michael Smith, Jacob Marc Robinson, J C Hawks, P Starbuck, Steven K CharlesAbstract:Competitive Figure?skaters experience substantial, repeated impact loading during jumps and landings. Although these loads, which are thought to be as high as six times body weight, can lead to overuse injuries, it is not currently possible to measure these forces on-ice. Consequently, efforts to improve safety for skaters are significantly limited. Here we present the development of an instrumented Figure?Skating blade for measuring forces on-ice. The measurement system consists of strain gauges attached to the blade, Wheatstone bridge circuit boards, and a data acquisition device. The system is capable of measuring forces in the vertical and horizontal directions (inferior?superior and anterior?posterior directions, respectively) in each stanchion with a sampling rate of at least 1000?Hz and a resolution of approximately one-tenth of body weight. The entire system weighs 142?g and fits in the space under the boot. Calibration between applied and measured force showed excellent agreement (R?>?0.99), and a preliminary validation against a force plate showed good predictive ability overall (R???0.81 in vertical direction). The system overestimated the magnitude of the first and second impact peaks but detected their timing with high accuracy compared to the force plate.
Bing Zhang - One of the best experts on this subject based on the ideXlab platform.
-
Learning to score and summarize Figure Skating sport videos.
2018Co-Authors: Bing Zhang, Fu Yanwei, Changmao Cheng, Jiang Yugang, Xue XiangyangAbstract:This paper focuses on fully understanding the Figure Skating sport videos. In particular, we present a large-scale Figure Skating sport video dataset, which include 500 Figure Skating videos. On average, the length of each video is 2 minute and 50 seconds. Each video is annotated by three scores from nine different referees, i.e., Total Element Score(TES), Total Program Component Score (PCS), and Total Deductions(DED). The players of this dataset come from more than 20 different countries. We compare different features and models to predict the scores of each video. We also derive a video summarization dataset of 476 videos with the ground-truth video summary produced from the great shot. A reinforcement learning based video summarization algorithm is proposed here; and the experiments show better performance than the other baseline video summarization algorithms.
-
Learning to score the Figure Skating sports videos
arXiv: Multimedia, 2018Co-Authors: Fu Yanwei, Zitian Chen, Yu-gang Jiang, Bing Zhang, Xiangyang XueAbstract:This paper targets at learning to score the Figure Skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale Figure Skating sports video dataset -- FisV dataset. This dataset includes 500 Figure Skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the Figure Skating videos.
-
Learning to Score Figure Skating Sport Videos
IEEE Transactions on Circuits and Systems for Video Technology, 1Co-Authors: Chengming Xu, Yanwei Fu, Zitian Chen, Bing Zhang, Yu-gang JiangAbstract:This paper aims at learning to score the Figure Skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale Figure Skating sports video dataset FisV dataset. This dataset includes 500 Figure Skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the Figure Skating videos. The codes and datasets would be downloaded from https://github.com/loadder/MS_LSTM.git.
M A Looney - One of the best experts on this subject based on the ideXlab platform.
-
judging anomalies at the 2010 olympics in men s Figure Skating
Measurement in Physical Education and Exercise Science, 2012Co-Authors: M A LooneyAbstract:The purpose of this study was to determine if the 2010 Olympic Figure Skating judges had trouble scoring Plushenko and the transitions program component, and if the International Skating Union's (ISU) “corridor” method flagged the same judging anomalies as the Rasch analyses. A 3-facet (skater by program component by judge) Rasch rating scale analysis was conducted on nine judges' free skate scores for five program components for each of 24 skaters. A principal components analysis of the residuals, and the ISU corridor method were also performed. Some judges were not internally consistent in scoring Plushenko (estimated discrimination index = −0.69; MNSQs ≥ 2.66). The unusual scoring patterns for Judges 1 and 2 warrant further investigation whereas the ISU corridor method did not flag any judges for the way they scored Plushenko and Lysacek. The Rasch analyses appear to be more sensitive to judging anomalies than the ISU corridor method.
-
objective measurement of Figure Skating performance
Journal of outcome measurement, 1997Co-Authors: M A LooneyAbstract:Figure Skating uses the median rank aggregation system for determining medal winners. Unfortunately, the system can be influenced by idiosyncratic ratings made by some judges unlike the Skating ability measures from a many-facet Rasch analysis. These measures are constructed to be independent, as statistically possible, of item difficulties, judge severities, and the rating scale structure. A many-facet Rasch analysis was conducted on data from the controversial ladies event at the 1994 Olympics. The results illustrate how the idiosyncratic ratings of the judges were not accounted for by the median rank system, thus biasing the selection of the gold medal winner. All sports that rely on judges' ratings should investigate the use of a many-facet Rasch model in order to bring more objectivity and fairness to the winner selection process.
Zhao Jin-ping - One of the best experts on this subject based on the ideXlab platform.
-
Analyzing the Development of Chinese Individuals Figure Skating from the Two Terms of National Top Competitions
China Winter Sports, 2013Co-Authors: Zhao Jin-pingAbstract:In order to further explore the development of Chinese Figure Skating,with the methods of documental informations,observation,data statistics and other methods,the paper has a statistical comparison of top 6 individuals Figure skaters' trying difficult motions at the 12th National Winter Games and the 11th National Games.It finds that Chinese individuals skaters have a rising competitive ability with obviously increasing difficult jumps and more profound understanding of the rules.As a theoretical reference of Figure Skating training,it suggests improving the skaters' quality and stability of difficult technical motions,strengthening their Skating speed and requirements for physical power.
-
Analysis on the Ladies' Technical Strength of Chinese Figure Skating
China Winter Sports, 2011Co-Authors: Zhao Jin-pingAbstract:The distributive situation of Figure Skating gold medals at the winter national games will influence each delegation' medal ranking in Chinese national games.The skaters' technical performance from short program and free Skating at the 11th winter national games may be used for forecasting the distributive situation of Figure Skating gold medal at the coming 12th winter national games.With the methods of documentary information,participant observation,mathematical statistics and contrast,the paper analyzes the Figure skaters' technical performance,results and scores from short program and free Skating at the 11th winter games.It thinks that the jumps,spins and footwork of Chinese ladies Figure skaters are imbalanced.As a reference for improving the whole strength of Chinese ladies Figure Skating and better preparing the Figure Skating competition at the 12th winter games,it suggests improving the technical quality and difficulty in jumps,spins and footwork by understanding and using the competition rules according to the skaters' individual advantage.
-
Analysis of the Figure Skating Coaches' Duty
China Winter Sports, 2008Co-Authors: Zhao Jin-pingAbstract:Starting with the function of Figure Skating coaches professional role in athletic training,the article has a analysis of their duty as a leader,a teacher and handler.Basing on these duty,it establishes the content and standard of self-evaluation for them to have self inspection.The purpose is to improve the coaches' teaching effect and give a theoretic reference for them to become better leaders and builders of skiers.
-
Discussing the Composition of The Figure Skating Program Choreographer's Ability
China Winter Sports, 2007Co-Authors: Zhao Jin-pingAbstract:The choreographer for Figure Skating competition program is a professional designer who choreographs the competition program that suits the skater's athletic level,and one of the main factors that affect the skater's competition program components.Recently in our country lacking of the high-level choreographers is one of the main factors that limit the whole level and result development of our country's Figure Skating.This article expatiates on the ability composition possessed by the Figure Skating program choreographer.The discussion will make some reference in developing the choreographers' level.
-
Application of Psychological training in Figure Skating training and matches
China Winter Sports, 2007Co-Authors: Zhao Jin-pingAbstract:Psychological training gives Figure Skating of training and games a great support. The skaters must have the better self-control. It is very important for the skaters to have the psychological training method in the training and games.