Sports action classification representing complex body postures and player-object interactions, is an emerging area in image-based sports analysis. Some works have contributed to automated sports action recognition using machine learning techniques over the past decades. However, sufficient image datasets representing women’s sports actions with enough intra- and inter-class variations are not available to the researchers. To overcome this limitation, this work presents a new dataset named WomenSports for women’s sports classification using small-scale training data. This dataset includes a variety of sports activities, covering wide variations in movements, environments, and interactions among players. In addition, this study proposes a convolutional neural network (CNN) for deep feature extraction. A channel attention scheme upon local contextual regions is applied to refine and enhance feature representation. The experiments are carried out on three different sports datasets and one dance dataset for generalizing the proposed algorithm, and the performances on these datasets are noteworthy. The deep learning method achieves 89.15% top-1 classification accuracy using ResNet-50 on the proposed WomenSports dataset, which is publicly available for research at Mendeley Data.
HostKIvaŝić-KosM.An overview of human action recognition in sports based on computer vision. Heliyon2022; 8(6): e09633.
2.
JayakumarBGovindarajanN.Multi-sensor fusion based optimized deep convolutional neural network for boxing punch activity recognition. Proc IMechE, Part P: J Sports Engineering and Technology2024. https://doi.org/10.1177/17543371241237085
3.
AgarwalAJhaPJainO, et al. POA-net: dance poses and activity classification using convolutional neural networks. In: 2024 IEEE region 10 symposium (TENSYMP), New Delhi, India, 27–29 September 2024, pp.1–6. New York, NY: IEEE.
4.
AslanyanM.On mobile pose estimation and action recognition design and implementation. Pattern Recognition and Image Analysis2024; 34(1): 126–136.
5.
BeraAWhartonZLiuY, et al. Attend and guide (AG-Net): a keypoints-driven attention-based deep network for image recognition. IEEE Trans Image Process2021; 30: 3691–3704.
6.
WongPMyintHDooleyL, et al. A multi-view automatic table tennis umpiring framework. Proc IMechE, Part P: J Sports Engineering and Technology2023; 238: 339–351.
7.
KomoriHIsogawaMMikamiD, et al. Time-weighted motion history image for human activity classification in sports. Sports Eng2023; 26(1): 45.
8.
BeraANasipuriMKrejcarO, et al. Fine-grained sports, yoga, and dance postures recognition: a benchmark analysis. IEEE Trans Instrum Meas2023; 72: 1–13.
9.
RayPBeraAKrejcarO, et al. Wsports-50: an image dataset for women’s sport action classification. In: Proceedings of 4th international conference frontiers in computing and systems (COMSYS 2023), Indian Institute of Technology Mandi, Himachal Pradesh, India, 16–17 October 2023, pp.457–469. CHAM: Springer.
10.
NaikBTHashmiMFBokdeND.A comprehensive review of computer vision in sports: open issues, future trends and research directions. Appl Sci2022; 12(9): 4429.
11.
Vidal-CodinaFEvansNEl FakirB, et al. Automatic event detection in football using tracking data. Sports Eng2022; 25(1): 18.
12.
LangSWildRIsenkoA, et al. Predicting the in-game status in soccer with machine learning using spatiotemporal player tracking data. Sci Rep2022; 12(1): 16291.
13.
BassekMRaabeDBanningA, et al. Analysis of contextualized intensity in men’s elite handball using graph- based deep learning. J Sports Sci2023; 41(13): 1299–1308.
14.
JohnsonSEveringhamM. Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of British machine vision conference, BMVC 2010, Aberystwyth, UK, 31 August–3 September 2010, pp.12.1–12.11. BMVA.
15.
LanTWangYMoriG.Discriminative figure-centric models for joint action localization and recognition. In: 2011 international conference computer vision, Barcelona, 6–13 November 2011, pp.2003–2010. New York, NY: IEEE.
16.
KarpathyATodericiGShettyS, et al. Large-scale video classification with convolutional neural networks. In: Proceedings of 2014 IEEE conference on computer vision and pattern recognition, Columbus, OH, USA, 23–28 June 2014, pp.1725–1732. New York, NY: IEEE.
17.
ShakyaSRZhangCZhouZ. Basketball-51: a video dataset for activity recognition in the basketball game. In: 11th international conference on computer science and information technology (CCSIT 2021), AIRCC Publishing Corporation, 29–30 May 2021. Canada: Vancouver.
18.
ThomasGGadeRMoeslundTB, et al. Computer vision for sports: current applications and research topics. Comput Vis Image Understand2017; 159: 3–18.
19.
DaiCLiuXLaiJ.Human action recognition using two-stream attention based LSTM networks. Appl Soft Comput2020; 86: 105820.
20.
DuW.The computer vision simulation of athlete’s wrong actions recognition model based on artificial intelligence. IEEE Access2024; 12: 6560–6568.
21.
DuDChaiLLiM, et al. Extracting features from foul actions of basketball players in real time using machine vision. Int J Comput Intell Syst2024; 17(1): 67.
22.
ShaoYHeZ.Var-yolov8s: IoT-based automatic foul detection in soccer matches. Alex Eng J2025; 111: 555–565.
23.
ZhangL.Deep learning based fine-grained recognition technology for basketball movements. Syst Soft Comput2024; 6: 200134.
24.
ZhouZZhangHEffatparvarM.Improved sports image classification using deep neural network and novel tuna swarm optimization. Sci Rep2024; 14(1): 14121.
25.
PajakGKrutzPPatalas-MaliszewskaJ, et al. An approach to sport activities recognition based on an inertial sensor and deep learning. Sens Actuators A Phys2022; 345: 113773.
26.
HwangJParkSKwakN.Athlete pose estimation by a global-local network. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), Honolulu, HI, USA, 21–26 July 2017, pp.58–65. New York, NY: IEEE.
27.
LiaoH.Coordination attention mechanism integrated yolov5 and k-means clustering for athlete’s posture balance control evaluation. In: 2024 international conf. data science and network security (ICDSNS), Tiptur, India, 26–27 July 2024, pp.1–4. New York, NY: IEEE.
28.
KhobdehSBYamaghaniMRSareshkehSK.Basketball action recognition based on the combination of yolo and a deep fuzzy LSTM network. J Supercomput2024; 80(3): 3528–3553.
29.
ZalluhogluCIkizler-CinbisN.Collective sports: a multi- task dataset for collective activity recognition. Image Vis Comput2020; 94: 103870.
30.
RodriguezMDAhmedJShahM.Action MACH a spatio-temporal maximum average correlation height filter for action recognition. In: 2008 IEEE conference on computer vision and pattern recognition, Anchorage, AK, USA, 23–28 June 2008, pp. 1–8. New York, NY: IEEE.
31.
Van ZandyckeGSomersVIstasseM, et al. DeepSportradar-v1: computer vision dataset for sports understanding with high quality annotations. In: Proceedings of the 5th international ACM workshop on multimedia content analysis in sports, Lisboa, Portugal, 14 October 2022, pp.1–8. New York, NY: ACM.
32.
CuiYZengCZhaoX, et al. SportsMot: a large multi-object tracking dataset in multiple sports scenes. In: Proceedings 2023 IEEE/CVF international conference on computer vision (ICCV), Paris, France, 1–6 October 2023, pp.9921–9931. New York, NY: IEEE.
33.
IngwersenCKMikkelstrupCMJensenJN, et alSportspose- a dynamic 3d sports pose dataset. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition. pp. 5218–5227.
34.
LiYChenLHeR, et al. Multisports: a multi-person video dataset of spatio-temporally localized sports actions. In: Proceedings of 2021 IEEE/CVF international conference on computer vision (ICCV), Montreal, QC, Canada, 10–17 October 2021, pp.13536–13545. New York, NY: IEEE.
35.
RyuKKimHLeeS.A deep learning model based on sequential object feature accumulation for sport activity recognition. Multimed Tools Appl2023; 82: 37387–37406.
36.
JohnsonSEveringhamM.Learning effective human pose estimation from inaccurate annotation. In: IEEE/CVF conference of computer vision and pattern recognition, Colorado Springs, CO, USA, 20–25 June 2011, pp. 1465–1472. New York, NY: IEEE.
37.
LiXUllahR.An image classification algorithm for football players’ activities using deep neural network. Soft Comput2023; 27(24): 19317–19337.
38.
SenAHossainSMMRussoMA, et al. Fine-grained soccer actions classification using deep neural network. In: 2022 15th international conference human system interaction (HSI), Melbourne, Australia, 28–31 July 2022, pp.1–6. New York, NY: IEEE.
39.
RussomannoTGBlaubergerPKolbingerO, et al. Drone-based position detection in sports—validation and applications. Front Physiol2022; 13: 850512.
40.
ŞahMDirekoğluC.Review and evaluation of player detection methods in field sports: comparing conventional and deep learning based methods. Multimed Tools Appl2023; 82(9): 13141–13165.
41.
HollausBReiterBVolmerJC.Catch recognition in automated American football training using machine learning. Sensors2023; 23(2): 840.
42.
HongJFisherMGharbiM, et al. Video pose distillation for few-shot, fine-grained sports action recognition. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 10–17 October 2021, pp.9254–9263. New York, NY: IEEE.
43.
WanyanYYangXDongW, et al. A comprehensive review of few-shot action recognition. arXiv:240714744 2024.
44.
Kumar DwivediSGuptaVMitraR, et al. ProtoGAN: towards few-shot learning for action recognition. In: Proceedings of the IEEE/CVF international conference on computer vision workshops, Seoul, Korea (South), 27–28 October 2019, pp.1308–1316. New York, NY: IEEE.
45.
ZamABohlooliAJamshidiK.Unsupervised deep domain adaptation algorithm for video based human activity recognition via recurrent neural networks. Eng Appl Artif Intell2024; 136: 108922.
46.
WooSParkJLeeJY, et al. CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 8–14 September 2018, pp.3–19. Berlin, Heidelberg: Springer-Verlag.
47.
HuJShenLSunG.Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 18–23 June 2018, pp.7132–7141. New York, NY: IEEE.
48.
BrigatoLIocchiL. A close look at deep learning with small data. In: 2020 25th international conference pattern recognition (ICPR), Milan, Italy, 10–15 January 2021, pp.2490–2497. New York, NY: IEEE.
49.
BeheraAWhartonZHewageP, et al. Context-aware attentional pooling (CAP) for fine-grained visual classification. Proc AAAI Conf Artif Intell35(2): 929–937.
50.
LiQLeiJRenC, et al. Research on sports image classification method based on SE-RES-CNN model. Sci Rep2024; 14(1): 19087.
51.
SelvarajuRRCogswellMDasA, et al. Grad-cam: visual explanations from deep networks via gradient-based localization. In: IEEE international conference computer vision (ICCV), Venice, Italy, 22-29 October 2017, pp.618–626. New York, NY: IEEE.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
