FSD-10: A fine-grained classification dataset for figure skating

Liu, Shenglan; Liu, Xiang; Huang, Gao; Qiao, Hong; Hu, Lianyu; Jiang, Dong; Zhang, Aibin; Liu, Yang; Guo, Guijie

doi:10.1016/j.neucom.2020.06.108

Cited by 16 publications

(8 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scoring in figure skating. Research on automatic scoring in figure skating can be broadly divided into two categories: those attempting to predict the overall score [32,33] and those assistance systems in scoring the technical scores [3,14,24]. Xu et al proposed the automatic scoring system as a single end-to-end framework [33].…”

Section: Related Workmentioning

confidence: 99%

“…To evaluate athletes so that the basis for scoring is more clearly defined, it is desirable to automate judging individual items according to the rules. Liu et al proposed an automated system to classify jumps, spins, and steps [14]. Delmastro et al also automated classification for six jump types in figure skating (Axel, Salchow, Toe Loop, Loop, Flip, and Lutz) [3].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Edge Error Judgment in Figure Skating Using 3D Pose Estimation from a Monocular Camera and IMUs

Tanaka,

Suzuki,

Takeda

et al. 2023

Proceedings of the 6th International Workshop on Multimedia Content Analysis in Sports

View full text Add to dashboard Cite

Automatic evaluating systems are fundamental issues in sports technologies. In many sports, such as figure skating, automated evaluating methods based on pose estimation have been proposed. However, previous studies have evaluated skaters' skills in 2D analysis. In this paper, we propose an automatic edge error judgment system with a monocular smartphone camera and inertial sensors, which enable us to analyze 3D motions. Edge error is one of the most significant scoring items and is challenging to automatically judge due to its 3D motion. The results show that the model using 3D joint position coordinates estimated from the monocular camera as the input feature had the highest accuracy at 83% for unknown skaters' data. We also analyzed the detailed motion analysis for edge error judgment. These results indicate that the monocular camera can be used to judge edge errors automatically. We will provide the figure skating single Lutz jump dataset, including pre-processed videos and labels at https://github.com/ryota-takedalab/JudgeAI-LutzEdge.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Automatic Edge Error Judgment in Figure Skating Using 3D Pose Estimation from a Monocular Camera and IMUs

Tanaka,

Suzuki,

Takeda

et al. 2023

Proceedings of the 6th International Workshop on Multimedia Content Analysis in Sports

View full text Add to dashboard Cite

show abstract

“…FSD-10 To fully evaluate the effectiveness of spatialtemporal modules in our network, FSD-10 [54] is involved in our experiments. FSD-10 collects 1484 clips from the worldwide figure skating championships in 2017-2018 and contains ten fine-grained actions in men/ladies' programs.…”

Section: A Datasetsmentioning

confidence: 99%

Spatial-Temporal Attention Network with Multi-similarity Loss for Fine-Grained Skeleton-Based Action Recognition

Liu

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Graph convolutional networks have been widely used in skeleton-based action recognition. However, existing approaches are limited in fine-grained action recognition due to the similarity of inter-class data. Moreover, the noisy data from pose extraction increases the challenge of fine-grained recognition. In this work, we propose a flexible attention block called Channel-Variable Spatial-Temporal Attention (CVSTA) to enhance the discriminative power of spatial-temporal joints and obtain a more compact intra-class feature distribution. Based on CVSTA, we construct a Multi-Dimensional Refinement Graph Convolutional Network (MDR-GCN), which can improve the discrimination among channel-, joint-and frame-level features for fine-grained actions. Furthermore, we propose a Robust Decouple Loss (RDL), which significantly boosts the effect of the CVSTA and reduces the impact of noise. The proposed method combining MDR-GCN with RDL outperforms the known stateof-the-art skeleton-based approaches on fine-grained datasets, FineGym99 and FSD-10, and also on the coarse dataset NTU-RGB+D X-view version.

show abstract

“…Compared to action recognition in videos [3], [4], [5], skeleton data is more compact in 2D [6], [7] or 3D [8], [9] format and suffering less from camera motion, light transformations, viewpoint changing and background noise, which makes it more focused on action representations. Thus, skeleton-based action recognition is an active task with broad real-world applications, including rehabilitation [10], [11], professional sports [12], augmented/virtual reality, and recognition in the wild [5], [13].…”

Section: Introductionmentioning

confidence: 99%

Fully Attentional Network for Skeleton-Based Action Recognition

Liu¹,

Zhou²

2023

IEEE Access

View full text Add to dashboard Cite

With the extraordinary ability by representing human body structure as a spatial graph, graph convolution networks (GCNs) have progressed much in skeleton-based action recognition. However, these methods usually use a predefined graph to represent human body structure, which is limited to 1-hop neighborhood with fixed weights. To handle these limitations, we propose a fully attentional network (FAN). It dynamically computes the edge weights for each input sample between graph nodes, thus avoiding the predefined fixed weights. Besides, it could attend to distant nodes by calculating their edge weights based on their similarities, thus avoiding the limited spatial receptive field. As an effective feature extractor, FAN achieves new state-of-the-art accuracy on three large-scale datasets, i.e., NTU RGB+D 60, NTU RGB+D 120 and Kinetics Skeleton 400. Visualizations are given to verify that FAN could dynamically emphasize the graph nodes that are important in expressing an action.

show abstract

FSD-10: A fine-grained classification dataset for figure skating

Cited by 16 publications

References 55 publications

Automatic Edge Error Judgment in Figure Skating Using 3D Pose Estimation from a Monocular Camera and IMUs

Automatic Edge Error Judgment in Figure Skating Using 3D Pose Estimation from a Monocular Camera and IMUs

Spatial-Temporal Attention Network with Multi-similarity Loss for Fine-Grained Skeleton-Based Action Recognition

Fully Attentional Network for Skeleton-Based Action Recognition

Contact Info

Product

Resources

About