Hasil untuk "Sports"

Si-En Hong, James Tribble, Alexander Lake et al.

From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of motion analysis in sports and other fast-movement scenarios. To bridge this gap, we propose a real-time motion focus recognition method that estimates the subject's locomotion intention from any egocentric video. We leverage the foundation model for camera pose estimation and introduce system-level optimizations to enable efficient and scalable inference. Evaluated on a collected egocentric action dataset, our method achieves real-time performance with manageable memory consumption through a sliding batch inference strategy. This work makes motion-centric analysis practical for edge deployment and offers a complementary perspective to existing egocentric studies on sports and fast-movement activities.

Ang Li, Xinyang Gong, Bozhou Chen et al.

We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced adversarial sports. The environment is grounded in elite-player match data and employs explicit probabilistic models to simulate rally-level dynamics, enabling realistic and interpretable agent-opponent interactions without relying on physics-based simulation. In this demonstration, we showcase multiple trained agents within ShuttleEnv and provide live, step-by-step visualization of badminton rallies, allowing attendees to explore different play styles, observe emergent strategies, and interactively analyze decision-making behaviors. ShuttleEnv serves as a reusable platform for research, visualization, and demonstration of intelligent agents in sports AI. Our ShuttleEnv demo video URL: https://drive.google.com/file/d/1hTR4P16U27H2O0-w316bR73pxE2ucczX/view

Nancy Yesenia Ortiz-Garcia, Diego Eduardo Rueda-Capristran, Ajay Kumar et al.

Abstract Background Neuromuscular diseases (NMDs) can impair respiratory muscle function, leading to increased morbidity and mortality. Respiratory muscle training (RMT) is widely used to manage these respiratory complications, but its efficacy across different NMDs remains unclear. This systematic review and meta-analysis evaluated the impact of physiotherapy interventions, specifically RMT, on respiratory muscle function in NMD patients. Methods A systematic search of multiple databases, including MEDLINE, EMBASE, Web of Science, Cochrane, CRS-Web, PEDro, LILACS, ICTPR, the China National Knowledge Infrastructure database, and ClinicalTrials.gov, was conducted up to February 2025. Randomized controlled trials (RCTs) and cohort studies evaluating RMT’s effect on lung volumes and respiratory muscle strength in NMD patients were included. Risk of bias assessment was performed using Cochrane Risk of bias tool for RCTs and Newcastle-Ottawa Scale for cohorts. Meta-analyses were performed using a random-effects model, and heterogeneity was assessed with I² statistics. Results Sixteen studies were analyzed from 9,626 screened articles. The meta-analysis demonstrated significant improvements in respiratory muscle strength, particularly in maximal inspiratory pressure (MD: 6.83 cmH₂O, 95% CI: 2.08 to 11.58, p < 0.01, I² = 3.8%) and maximal expiratory pressure (MD: 13.05 cmH₂O, 95% CI: 3.65to 22.42, p < 0.01, I² = 43%). No significant improvements were observed in forced vital capacity (MD: 3.13%, 95% CI: -8.06 to 14.34, p = 0.58), sniff nasal inspiratory pressure (MD: 1.47 cmH₂O, 95% CI: -15.45 to 18.39, p = 0.86), forced expiratory volume in one second (MD: -0.02 L, 95% CI: -0.17 to 0.13, p = 0.78), and vital capacity (MD: -0.10 L, 95% CI: -0.31 to 0.11, p = 0.33). Conclusion This review supports the role of respiratory muscle training in improving inspiratory and expiratory muscle strength in patients with neuromuscular diseases. However, variability in study methodologies and patient populations limits the statistical significance of some respiratory parameters. Future studies should aim to standardize interventions and outcome measures to provide more conclusive evidence on the efficacy of RMT.

Li Che, Yijia Zhou, Ying Wang

BackgroundPilates Reformer training is a scientifically validated method for enhancing body control. However, research on its application to improve the technical quality of Latin dance movements, particularly the Cha-Cha circular chase step, is limited. This study aims to evaluate the effectiveness of Pilates Reformer training in enhancing this technique, with the goal of providing a theoretical foundation for its use in improving Latin dance performance and preventing injuries.MethodsOur study involved 18 Latin dance students specializing in sports dance, aged 18–30 years, with at least 3 years of Latin dance experience. Participants were randomly assigned to an experimental group (n = 9) and a control group (n = 9). Over a 12-week period, the experimental group underwent Pilates Reformer training, while the control group continued with their regular training. Biomechanical data were collected before and after each session to assess joint angles, movement speed, muscle activation, and technical quality scores using the WDSF 3.0 evaluation criteria. Data analysis and visualization were performed using Graph Prism 10.0 software, and statistical analyses were conducted with SPSS software (Version 22). Paired-sample t-tests were used for within-group comparisons, and independent-sample t-tests were used for between-group comparisons, with a significance level set at p &lt; 0.05.Results(1) The experimental group showed significant (P &lt; 0.05) or highly significant (P &lt; 0.01) differences in the joint angles of the hip, knee, and ankle at key points across all three axes (X, Y, Z) compared to the control group. The experimental group also exhibited significant improvements (P &lt; 0.05) in the flexion and extension speeds of these joints during the movement phases, while the control group showed minimal changes (P &gt; 0.05). (2) Pilates Reformer training led to significant increases (P &lt; 0.05 or P &lt; 0.01) in the RMS normalized muscle activation values in both legs during the Cha-Cha circular chase step. In contrast, the control group showed increased iEMG values, but these did not reach statistical significance (P &gt; 0.05). (3) The experimental group showed significant improvements (P &lt; 0.05) in posture (B1), foot movements (B4), and Latin characteristics (B5), as well as highly significant improvements (P &lt; 0.01) in basic movements (B6) and preparation-action-recovery (B7) compared to the control group. Additionally, the experimental group exhibited consistent improvements in the average TQ scores across all evaluated components.ConclusionPilates Reformer training significantly enhances joint angles, movement speeds, muscle activation, and technical quality in Latin dance, particularly the Cha-Cha circular chase step. These findings demonstrate the potential of Pilates Reformer training to improve dance technique, optimize movement quality, and support injury prevention in Latin dance athletes, providing strong evidence for its effectiveness in this domain.

László Csató, András Gyimesi

A match played in a sports tournament can be called stakeless if at least one team is indifferent to its outcome because it already has qualified or has been eliminated. Such a game threatens fairness since teams may not exert full effort without incentives. This paper suggests a novel classification for stakeless matches based on their expected outcome: they are more costly if the indifferent team is more likely to win by playing honestly. Our approach is illustrated with the 2026 FIFA World Cup, the first edition of the competition with 48 teams. We propose a novel format based on imbalanced groups, which substantially reduces the probability of stakeless matches played by the strongest teams according to Monte Carlo simulations. The new design also increases the uncertainty of match outcomes and requires fewer matches. Governing bodies in sports are encouraged to consider our innovative idea in order to enhance the competitiveness of their tournaments.

Tiago Mendes-Neves, Yassine Baghoussi, Luís Meireles et al.

Forecasting sporting events encapsulate a compelling intellectual endeavor, underscored by the substantial financial activity of an estimated $80 billion wagered in global sports betting during 2022, a trend that grows yearly. Motivated by the challenges set forth in the Springer Soccer Prediction Challenge, this study presents a method for forecasting soccer match outcomes by forecasting the shot quantity and quality distributions. The methodology integrates established ELO ratings with machine learning models. The empirical findings reveal that, despite the constraints of the challenge, this approach yields positive returns, taking advantage of the established market odds.

Maciej Superson, Klaudia Wilk-Trytko, Katarzyna Szmyt et al.

Intruduction and purpose: Patients with severe asthma account for approximately 3% to 10% of all asthma patients. They have higher hospital utilization rates and treatment costs than patients with non-severe asthma. Previously, treatment options for these patients were limited due to unacceptable side effects. However, the advent of biologic therapies has provided promising targeted therapy for these patients. State of knowledge: Biologic therapies target inflammatory modulators that play a key role in the pathogenesis of asthma, particularly in patients with high T2 cells. These therapies have shown promising results in reducing asthma symptoms, improving lung function, decreasing the use of oral corticosteroids, and enhancing patients' quality of life. Conclusions: This article reviews the mechanism of action, efficacy, and indications of currently approved biologic drugs available in Poland, as well as potential therapeutic targets for the future.

Sigurður Benediktsson, Erlingur Johannsson, Erlingur Johannsson et al.

The organisation and development strategies of youth soccer differ between Norway and Iceland. Whether this affect physical capacity is unknown. Thus, the first aim of the present study is to compare physical capacity between players from Iceland and Norway. Secondary aim is to assess associations between biological maturity and physical capacity in the Icelandic players since an association previously has been shown among the Norwegians. There were 48 U14 players from Iceland included and 103 players from Norway. Bone age (BA), measured with left-wrist x-ray, was used as an indicator of biological maturity. To measure physical capacity, 40 metre (m) linear sprint, standing long jump (SLJ), countermovement jump (CMJ), the Yo-Yo intermittent recovery test (IR1-test) and a maximal oxygen uptake test (VO2max) were used. Training load was assessed by questionnaire. The results showed that the Norwegian players ran faster (5.90 ± 0.38 vs. 6.37 ± 0.44 s, p &lt; .001), had better intermittent endurance capacity (1,235 ± 461 vs. 960 ± 423 m, p &lt; .001) and higher VO2max, (60.3 ± 6.5 vs. 54.8 ± 5.3 ml·kg−1·min−1, p &lt; .001) than the Icelandic players. The players from Norway reported a higher number of weekly organised soccer training hours than the Icelandic. We also found significant correlations between BA and performance on 40 m linear sprint (r = −.566, p &lt; .001), SLJ (r = .380, p = .008) and CMJ (r = .354, p = .014) among the Icelandic players. Moreover, no correlations were found between BA and VO2max or intermittent endurance capacity. In conclusion, the Norwegian players ran faster and had better VO2max and intermittent endurance capacity than the Icelandic players. Biological maturity level was associated with speed and jumping performance in U14 soccer players in Iceland, but not with VO2max or intermittent endurance capacity. Findings indicate that more research is needed to investigate the influence of different organisation and structure of youth soccer between the two countries on physical capacity.

Verner Marijančić, Stanislav Peharec, Gordana Starčević-Klasan et al.

<b>Background/Aim:</b> University students are a particularly vulnerable population, as they spend increasing amounts of time sitting, which poses a major threat to their musculoskeletal health and posture. The aim of this cross-sectional study was to investigate gender differences in the relationships between physical activity (PA) and sedentary behavior, spinal curvatures and mobility, the endurance and balance of the trunk muscles, and the possible presence of non-specific low back pain (NS-LBP) in young adults aged 18–25 years. <b>Methods:</b> A total of 139 students completed all required tests. <b>Results:</b> Male students engaged in significantly more PA related to recreation, sports and leisure and were significantly more likely to be hyperkyphotic than female students. The more the male students participated in sports, the more pronounced the thoracic kyphosis. Female students had significantly more pronounced lumbar lordosis and anterior pelvic tilt that correlated with lumbar lordosis. Female students generally had significantly higher trunk extensor endurance and more balanced trunk musculature than males. NS-LBP correlated with PA in female students who generally had higher levels of NS-LBP than male students, with a statistically significant difference between those who practiced the most PA. <b>Conclusions:</b> Our results suggest that female students practice less PA and have pronounced lordosis and trunk extensor endurance, in contrast to males who practice more PA and have pronounced trunk flexor endurance and hyperkyphosis. Our findings suggest that more PA should be encouraged but implemented with caution and as an individualized gender-specific approach to prevent postural deformities and chronic musculoskeletal disorders, including NS-LBP.

Kevin Ho, BSc DPM (UWA), Paul S Armanasco, BSc MSc FACPS FFPM RCPS (Glas)

Introduction: A large proportion of patients with chronic lateral ankle instability suffer from recurrent ankle sprains and develop concurrent peroneal tendon pathology. This is associated with significant pain, post-traumatic ankle osteoarthritis and severe impairments in quality of life. Currently, evidence-based treatment guidelines for peroneal pathology are lacking despite a high failure rate with nonoperative management of tears or ruptures. This case report details the first cited peroneal L-lengthening tenodesis and modified Brostrom-Gould to date. Case presentation: A 56-year-old male presented with chronic pain, disability and instability following a forced ankle plantarflexion-inversion injury. The patient was diagnosed with a complete rupture of the peroneus brevis tendon at the level of the retro-malleolar groove with 5 cm retraction, marked peroneal tenosynovitis and tendinopathy, and chronic lateral ankle ligament deficiency. Surgical management was successful, involving an L-lengthening peroneal tendon repair and tenodesis, with a concurrent modified Brostrom-Gould procedure. Following 12 months follow-up after” surgical management, the patient returned to activities of normal living and sports with significant improvements in pain levels and reported quality of life. Conclusions: A high index of suspicion is necessary for peroneal tendon injury following inversion ankle trauma, especially in the presence of chronic ankle instability. The reported surgical technique may be considered as a feasible option for patients with chronic ankle instability and concurrent peroneal tendon rupture. Further research is warranted to establish evidence-based guidelines to facilitate clinical decision-making.

Lijie Yao, Anastasia Bezerianos, Romain Vuillemot et al.

Competitive sports coverage increasingly includes information on athlete or team statistics and records. Sports video coverage has traditionally embedded representations of this data in fixed locations on the screen, but more recently also attached representations to athletes or other targets in motion. These publicly used representations so far have been rather simple and systematic investigations of the research space of embedded visualizations in motion are still missing. Here we report on our preliminary research in the domain of professional and amateur swimming. We analyzed how visualizations are currently added to the coverage of Olympics swimming competitions and then plan to derive a design space for embedded data representations for swimming competitions. We are currently conducting a crowdsourced survey to explore which kind of swimming-related data general audiences are interested in, in order to identify opportunities for additional visualizations to be added to swimming competition coverage.

Hongxin Li, Jingsheng Tang, Xuechao Xu et al.

In sensitive scenarios, such as meetings, negotiations, and team sports, messages must be conveyed without detection by non-collaborators. Previous methods, such as encrypting messages, eye contact, and micro-gestures, had problems with either inaccurate information transmission or leakage of interaction intentions. To this end, a novel gesture-free hand intention recognition scheme was proposed, that adopted surface electromyography(sEMG) and isometric contraction theory to recognize different hand intentions without any gesture. Specifically, this work includes four parts: (1) the experimental system, consisting of the upper computer software, self-conducted myoelectric watch, and sports platform, is built to get sEMG signals and simulate multiple usage scenarios; (2) the paradigm is designed to standard prompt and collect the gesture-free sEMG datasets. Eight-channel signals of ten subjects were recorded twice per subject at about 5-10 days intervals; (3) the toolbox integrates preprocessing methods (data segmentation, filter, normalization, etc.), commonly used sEMG signal decoding methods, and various plotting functions, to facilitate the research of the dataset; (4) the benchmark results of widely used methods are provided. The results involve single-day, cross-day, and cross-subject experiments of 6-class and 12-class gesture-free hand intention when subjects with different sports motions. To help future research, all data, hardware, software, and methods are open-sourced on the following website: click here.

Grzegorz Rypeść, Grzegorz Kurzejamski

This work introduces a novel end-to-end approach for estimating extrinsic parameters of cameras in multi-camera setups on real-life sports fields. We identify the source of significant calibration errors in multi-camera environments and address the limitations of existing calibration methods, particularly the disparity between theoretical models and actual sports field characteristics. We propose the Evolutionary Stitched Camera calibration (ESC) algorithm to bridge this gap. It consists of image segmentation followed by evolutionary optimization of a novel loss function, providing a unified and accurate multi-camera calibration solution with high visual fidelity. The outcome allows the creation of virtual stitched views from multiple video sources, being as important for practical applications as numerical accuracy. We demonstrate the superior performance of our approach compared to state-of-the-art methods across diverse real-life football fields with varying physical characteristics.

Ryan S. Brill, Ryan Yee, Sameer K. Deshpande et al.

Expected points is a value function fundamental to player evaluation and strategic in-game decision-making across sports analytics, particularly in American football. To estimate expected points, football analysts use machine learning tools, which are not equipped to handle certain challenges. They suffer from selection bias, display counter-intuitive artifacts of overfitting, do not quantify uncertainty in point estimates, and do not account for the strong dependence structure of observational football data. These issues are not unique to American football or even sports analytics; they are general problems analysts encounter across various statistical applications, particularly when using machine learning in lieu of traditional statistical models. We explore these issues in detail and devise expected points models that account for them. We also introduce a widely applicable novel methodological approach to mitigate overfitting, using a catalytic prior to smooth our machine learning models.

Yiqi Zhong, Luming Liang, Bohan Tang et al.

We introduce motion graph, a novel approach to the video prediction problem, which predicts future video frames from limited past data. The motion graph transforms patches of video frames into interconnected graph nodes, to comprehensively describe the spatial-temporal relationships among them. This representation overcomes the limitations of existing motion representations such as image differences, optical flow, and motion matrix that either fall short in capturing complex motion patterns or suffer from excessive memory consumption. We further present a video prediction pipeline empowered by motion graph, exhibiting substantial performance improvements and cost reductions. Experiments on various datasets, including UCF Sports, KITTI and Cityscapes, highlight the strong representative ability of motion graph. Especially on UCF Sports, our method matches and outperforms the SOTA methods with a significant reduction in model size by 78% and a substantial decrease in GPU memory utilization by 47%.

Małgorzata Siekańska

The purpose of this study was to investigate how rhythmic gymnastics coaches perceive the factors influencing sports talent development. Participants (30 female coaches) were administered a demographic survey, an open-ended questionnaire (a structured interview), and the Talent Development Environment Questionnaire (TDEQ PL). Mixed strategies (quantitative and qualitative) were used in the analysis. The research revealed two types of facilitators (essential vs. favorable), and two types of inhibitors (preclusive vs. disruptive). Within the essential facilitator factors, coaches most often indicated long-term motivation. Social support was perceived as a main favorable talent development factor. The child’s inadequate approach to training and inadequate parental involvement were indicated as the main preclusive talent development factors. Difficult situations (e.g., health problems) were enumerated as a major disruptive factor. The studied group of coaches recognized the Individualized Approach to Athlete (M=4.24) as the most important environmental factor that positively influences the development of talented athletes.

Shojaie Parham, Botchu Rajesh, Iyengar Karthikeyan et al.

To describe the sonographic appearance of pronator teres syndrome and the role of ultrasound-guided hydrodissection for its management.

Katja Ludwig, Julian Lorenz, Robin Schön et al.

Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines. In individual sports, these analyses mainly comprise the body posture. This paper focuses on the disciplines of triple, high, and long jump, which require fine-grained locations of the athlete's body. Typical human pose estimation datasets provide only a very limited set of keypoints, which is not sufficient in this case. Therefore, we propose a method to detect arbitrary keypoints on the whole body of the athlete by leveraging the limited set of annotated keypoints and auto-generated segmentation masks of body parts. Evaluations show that our model is capable of detecting keypoints on the head, torso, hands, feet, arms, and legs, including also bent elbows and knees. We analyze and compare different techniques to encode desired keypoints as the model's input and their embedding for the Transformer backbone.

Tica Lin, Zhutian Chen, Yalong Yang et al.

Sports game data is becoming increasingly complex, often consisting of multivariate data such as player performance stats, historical team records, and athletes' positional tracking information. While numerous visual analytics systems have been developed for sports analysts to derive insights, few tools target fans to improve their understanding and engagement of sports data during live games. By presenting extra data in the actual game views, embedded visualization has the potential to enhance fans' game-viewing experience. However, little is known about how to design such kinds of visualizations embedded into live games. In this work, we present a user-centered design study of developing interactive embedded visualizations for basketball fans to improve their live game-watching experiences. We first conducted a formative study to characterize basketball fans' in-game analysis behaviors and tasks. Based on our findings, we propose a design framework to inform the design of embedded visualizations based on specific data-seeking contexts. Following the design framework, we present five novel embedded visualization designs targeting five representative contexts identified by the fans, including shooting, offense, defense, player evaluation, and team comparison. We then developed Omnioculars, an interactive basketball game-viewing prototype that features the proposed embedded visualizations for fans' in-game data analysis. We evaluated Omnioculars in a simulated basketball game with basketball fans. The study results suggest that our design supports personalized in-game data analysis and enhances game understanding and engagement.