Hasil untuk "Sports"

R. Bahr, I. Holme

L. Jones, L. Sinnott, D. Mutti et al.

J. Cronin, K. Hansen

S. Barber-Westin, F. Noyes

Arushi Rai, Adriana Kovashka

Video-LLMs often attend to irrelevant frames, which is especially detrimental for sports coaching tasks requiring precise temporal grounding. Yet obtaining frame-level supervision is challenging: expensive to collect from humans and unreliable from other models. We improve temporal grounding without additional annotations by exploiting the observation that related tasks, such as generation and verification, must attend to the same frames. We enforce this via a self-consistency objective over select visual attention maps of tightly-related tasks. Using VidDiffBench, which provides ground-truth keyframe annotations, we first validate that attention misallocation is a significant bottleneck. We then show that training with our objective yields gains of +3.0%, +14.1% accuracy and +0.9 BERTScore over supervised finetuning across three sports coaching tasks: Exact, FitnessQA, and ExpertAF, even surpassing closed-source models.

Tica Lin, Ruxun Xiang, Gardenia Liu et al.

Video storytelling is essential for sports performance analysis and fan engagement, enabling sports professionals and fans to effectively communicate and interpret the spatial and temporal dynamics of gameplay. Traditional methods rely on manual annotation and verbal explanations, placing significant demands on creators for video editing skills and on viewers for cognitive focus. However, these approaches are time-consuming and often struggle to accommodate individual needs. SportsBuddy addresses this gap with an intuitive, interactive video authoring tool. It combines player tracking, embedded interaction design, and timeline visualizations to seamlessly integrate narratives and visual cues within game contexts. This empowers users to effortlessly create context-driven video stories. Since its launch, over 150 sports users, including coaches, athletes, content creators, parents and fans, have utilized SportsBuddy to produce compelling game highlights for diverse use cases. User feedback highlights its accessibility and ease of use, making video storytelling and insight communication more attainable for diverse audiences. Case studies with collegiate teams and sports creators further demonstrate SportsBuddy's impact on enhancing coaching communication, game analysis, and fan engagement.

Keivan Shariatmadar, Ahmad Osman

The integration of Artificial Intelligence (AI) into sports officiating represents a paradigm shift in how decisions are made in competitive environments. Traditional manual systems, even when supported by Instant Video Replay (IVR), often suffer from latency, subjectivity, and inconsistent enforcement, undermining fairness and athlete trust. This paper introduces 'FST.ai' -- which is developed under the 'R3AL.ai' project, which serves as its Principal Investigator: r3al.ai -- a novel AI-powered framework designed to enhance officiating in Sport Taekwondo, particularly focusing on the complex task of real-time head kick detection and scoring. Leveraging computer vision, deep learning, and edge inference, the system automates the identification and classification of key actions, significantly reducing decision time from minutes to seconds while improving consistency and transparency. Importantly, the methodology is not limited to Taekwondo. The underlying framework -- based on pose estimation, motion classification, and impact analysis -- can be adapted to a wide range of sports requiring action detection, such as judo, karate, fencing, or even team sports like football and basketball, where foul recognition or performance tracking is critical. By addressing one of Taekwondo's most challenging scenarios -- head kick scoring -- we demonstrate the robustness, scalability, and sport-agnostic potential of 'FST.ai' to transform officiating standards across multiple disciplines.

Dennis Krämer, Anja Bosold, Martin Minarik et al.

Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching. Empirical data on how students perceive the increasing influence of AI, which different types of tools they use, what they expect from them in their daily academic tasks, and their concerns regarding the use of AI in their studies are still limited. The manuscript presents findings from a quantitative survey conducted among sports students of all semesters in Germany using an online questionnaire. It explores aspects such as students' usage behavior, motivational factors, and uncertainties regarding the impact of AI tools on academia in the future. Furthermore, the social climate in sports studies is being investigated to provide a general overview of the current situation of the students in Germany. Data collection took place between August and November 2023, addressing all sports departments at German universities, with a total of 262 students participating. Our Findings indicate that students have a strong interest in using AI tools in their studies, expecting them to improve their overall academic performance, understand the complexity of scientific approaches, and save time. They express confidence that the proliferation of AI will not compromise their critical thinking skills. Moreover, students are positive about integrating more AI-related topics into the curriculum and about lecturers adopting more AI-based teaching methods. However, our findings also show that students have concerns about plagiarism, lecturer preparedness and their own skills and future skill development.

Enzo B Onofre, Leonardo M P Moraes, Cristina D Aguiar

This paper introduces AskSport, a question-answering web application about sports. It allows users to ask questions using natural language and retrieve the three most relevant answers, including related information and documents. The paper describes the characteristics and functionalities of the application, including use cases demonstrating its ability to return names and numerical values. AskSport and its implementation are available for public access on HuggingFace.

Hossein Feiz, David Labbé, Thomas Romeas et al.

We propose a novel framework for accurate 3D human pose estimation in combat sports using sparse multi-camera setups. Our method integrates robust multi-view 2D pose tracking via a transformer-based top-down approach, employing epipolar geometry constraints and long-term video object segmentation for consistent identity tracking across views. Initial 3D poses are obtained through weighted triangulation and spline smoothing, followed by kinematic optimization to refine pose accuracy. We further enhance pose realism and robustness by introducing a multi-person physics-based trajectory optimization step, effectively addressing challenges such as rapid motions, occlusions, and close interactions. Experimental results on diverse datasets, including a new benchmark of elite boxing footage, demonstrate state-of-the-art performance. Additionally, we release comprehensive annotated video datasets to advance future research in multi-person pose estimation for combat sports.

Chunggi Lee, Ut Gong, Tica Lin et al.

Injury prevention in sports requires understanding how bio-mechanical risks emerge from movement patterns captured in real-world scenarios. However, identifying and interpreting injury prone events from raw video remains difficult and time-consuming. We present VAIR, a visual analytics system that supports injury risk analysis using 3D human motion reconstructed from sports video. VAIR combines pose estimation, bio-mechanical simulation, and synchronized visualizations to help users explore how joint-level risk indicators evolve over time. Domain experts can inspect movement segments through temporally aligned joint angles, angular velocity, and internal forces to detect patterns associated with known injury mechanisms. Through case studies involving Achilles tendon and Anterior cruciate ligament (ACL) injuries in basketball, we show that VAIR enables more efficient identification and interpretation of risky movements. Expert feedback confirms that VAIR improves diagnostic reasoning and supports both retrospective analysis and proactive intervention planning.

Zoé Stehlin, Felix Karl-Ludwig Klingebiel, Hans-Christoph Pape et al.

<b>Background</b>: Although the difficulty level of figure skating programs has increased in the last two decades, particularly at the junior level, trends in performance have not been reported. This retrospective observational study investigated performance development trends among the top five junior figure skaters competing at international levels in both the ladies’ and men’s singles disciplines from 2005 to 2020. Data from 160 junior single ladies and 160 junior single men were analyzed. The focus was on the progression of technical elements—particularly jumps—and their potential correlation with injury risk. It was hypothesized that younger athletes are increasingly performing jumps with more revolutions, thereby enhancing overall competition standards. <b>Materials and Methods</b>: Using data from the Junior World Championships and Junior Grand Prix Finals, linear regression analysis and one-way ANOVA were conducted to track the frequency of double, triple, and quadruple jumps, as well as trends in age development among athletes in the singles categories from 2005 to 2020. <b>Results</b>: The results indicate a significant increase in the execution of higher-revolution jumps among junior athletes. Between 2005 and 2012, the frequency of double jumps declined across all events, with the most pronounced reductions observed in the Ladies’ Junior World Championships (Δ = 0.216, <i>p</i> = 0.004, d = 1.64) and the Men’s Junior World Championships (Δ = 0.500, <i>p</i> = 0.001, d = 1.82). From 2005 to 2011, the frequencies of triple and quadruple jumps increased, while double jumps remained stable or showed only slight increases. Triple jumps showed slight downward trends (e.g., R² = 0.0202 at the Men’s Junior World Championships). Although still rare, the frequency of quadruple jumps has shown a consistent upward trend across multiple competitions. Between 2000 and 2009, all four events exhibited declining age trends, with decreases ranging from −0.029 to −0.078 years of age per year. In the subsequent decade (2010–2020), when averaged across all events, the observed difference slope (Δ = 0.014) indicated a continued decline in athlete age. <b>Conclusions</b>: In summary, increases in more difficult jumps were found, with simultaneous decreases in less difficult jumps. As jump complexity rises, a parallel increase in sport-specific injury incidence can be anticipated, highlighting the need for proactive strategies for injury prevention and athlete well-being.

Nita Bandyopadhyay, Tuhin Das, Suvra Mondal

Background. Yoga, an ancient practice rooted in Indian culture, has gained global recognition for its physical and mental health benefits. Among its practices, Surya Namaskar (SN) stands out as a holistic yogic Sun Salutation exercise combining postures, breathing, and mindfulness, offering physical vitality, mental calmness, and a practical solution to the challenges posed by modern sedentary lifestyles. Objectives. The objective of the present systematic review was to analyze the effect of SN on overall health and wellness of healthy adults. Materials and methods. A comprehensive search was conducted in five major databases, namely Scopus, PubMed, PubMed Central, Web of Science, and ScienceDirect, using the terms such as “Surya Namaskar”, “Sun Salutation”,“Surya Namaskar and physical fitness”, “Surya Namaskar for adults”, “Sun Salutation for overall health and wellness”,and “Surya Namaskar and sedentary lifestyle”. The articles published in English between 2011 and 2024 were considered in the current review. The systematic search and reporting adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Quality Assessment Tool for Quantitative Studies was used to analyze the methodological quality of the included articles. Results. Based on the inclusion and exclusion criteria, 117 articles were initially retrieved, out of which 11 were finally included, encompassing data from 445 healthy adults from three countries, aged between 18 and 65 years. The duration of the SN intervention varied from four to 24 weeks, with session frequency ranging from three days per week to daily, and a diverse number of cycles. The methodological quality analysis revealed that two articles were of strong, six of moderate, and the remaining three of weak quality. Conclusions. This systematic review concludes that the practice of the yogic Sun Salutation exercise (SN) is beneficial for improving and maintaining physical fitness, physiological health, and psychological well-being, which determine the overall health and wellness of healthy adults.

N. Jayanthi, Courtney Pinkham, L. Dugas et al.

Context: Sports specialization is intense training in 1 sport while excluding others. Sports specialization in early to middle childhood has become increasingly common. While most experts agree that some degree of sports specialization is necessary to achieve elite levels, there is some debate as to whether such intense practice time must begin during early childhood and to the exclusion of other sports to maximize potential for success. There is a concern that sports specialization before adolescence may be deleterious to a young athlete. Evidence Acquisition: PubMed and OVID were searched for English-language articles from 1990 to 2011 discussing sports specialization, expert athletes, or elite versus novice athletes, including original research articles, consensus opinions, and position statements. Results: For most sports, there is no evidence that intense training and specialization before puberty are necessary to achieve elite status. Risks of early sports specialization include higher rates of injury, increased psychological stress, and quitting sports at a young age. Sports specialization occurs along a continuum. Survey tools are being developed to identify where athletes fall along the spectrum of specialization. Conclusion: Some degree of sports specialization is necessary to develop elite-level skill development. However, for most sports, such intense training in a single sport to the exclusion of others should be delayed until late adolescence to optimize success while minimizing injury, psychological stress, and burnout.

Kuangzhi Ge, Lingjun Chen, Kevin Zhang et al.

Recently, significant advances have been made in Video Large Language Models (Video LLMs) in both academia and industry. However, methods to evaluate and benchmark the performance of different Video LLMs, especially their fine-grained, temporal visual capabilities, remain very limited. On one hand, current benchmarks use relatively simple videos (e.g., subtitled movie clips) where the model can understand the entire video by processing just a few frames. On the other hand, their datasets lack diversity in task format, comprising only QA or multi-choice QA, which overlooks the models' capacity for generating in-depth and precise texts. Sports videos, which feature intricate visual information, sequential events, and emotionally charged commentary, present a critical challenge for Video LLMs, making sports commentary an ideal benchmarking task. Inspired by these challenges, we propose a novel task: sports video commentary generation, developed $\textbf{SCBench}$ for Video LLMs. To construct such a benchmark, we introduce (1) $\textbf{SCORES}$, a six-dimensional metric specifically designed for our task, upon which we propose a GPT-based evaluation method, and (2) $\textbf{CommentarySet}$, a dataset consisting of 5,775 annotated video clips and ground-truth labels tailored to our metric. Based on SCBench, we conduct comprehensive evaluations on multiple Video LLMs (e.g. VILA, Video-LLaVA, etc.) and chain-of-thought baseline methods. Our results found that InternVL-Chat-2 achieves the best performance with 5.44, surpassing the second-best by 1.04. Our work provides a fresh perspective for future research, aiming to enhance models' overall capabilities in complex visual understanding tasks. Our dataset will be released soon.

László Csató, Sergey Ilyin

UEFA declares that it is committed to respecting the fundamental values of sports. However, the qualification rules of the post-2024 UEFA Champions League are shown to be unfair: a game with misaligned incentives was narrowly avoided in the 2023/24 German Bundesliga. We develop a mathematical model to reveal how incentives for losing can be reduced or eliminated. Since UEFA repeatedly commits the same theoretical mistake in designing the qualification system of its competitions, governing bodies in sports are called to work more closely together with the scientific community.

Lukić-Nikolić Jelena, Lazarević Snežana, Antić Sunčica

This paper investigates how demographic factors (gender and age), and contextual factors (length of team membership and work type) affect communication, shared values, collaborative growth and improvements in agile software development teams in Serbia. Empirical research was conducted using a specially designed online questionnaire which consisted of profile questions and three highly reliable scales focusing on agile software development team communication, shared values, and collaborative growth and improvements. In the period from April to October 2024, a total of 107 agile software development team members from Serbia participated in the research. Data analysis was conducted using descriptive statistics, the Mann-Whitney U-test, and the Kruskal-Wallis H-test. The findings reveal no statistically significant differences in communication, shared values, or collaborative growth based on age, length of team membership, and work type. However, a notable gender difference was observed, with female team members reporting a higher level of agreement on shared values within their teams. These results underscore the critical role of gender dynamics in fostering a cohesive team environment in agile settings. Understanding these dynamics is essential for enhancing team collaboration and performance, suggesting that organizations should consider gender inclusivity when developing agile software development teams.

Asish Bera, Mita Nasipuri, Ondrej Krejcar et al.

Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification task due to the complex movement of body parts. Deep Convolutional Neural Networks (CNNs) have attained significantly improved performance in solving various human body-pose estimation problems. Though decent progress has been achieved in yoga postures recognition using deep learning techniques, fine-grained sports, and dance recognition necessitates ample research attention. However, no benchmark public image dataset with sufficient inter-class and intra-class variations is available yet to address sports and dance postures classification. To solve this limitation, we have proposed two image datasets, one for 102 sport categories and another for 12 dance styles. Two public datasets, Yoga-82 which contains 82 classes and Yoga-107 represents 107 classes are collected for yoga postures. These four SYD datasets are experimented with the proposed deep model, SYD-Net, which integrates a patch-based attention (PbA) mechanism on top of standard backbone CNNs. The PbA module leverages the self-attention mechanism that learns contextual information from a set of uniform and multi-scale patches and emphasizes discriminative features to understand the semantic correlation among patches. Moreover, random erasing data augmentation is applied to improve performance. The proposed SYD-Net has achieved state-of-the-art accuracy on Yoga-82 using five base CNNs. SYD-Net's accuracy on other datasets is remarkable, implying its efficiency. Our Sports-102 and Dance-12 datasets are publicly available at https://sites.google.com/view/syd-net/home.

Rui Luo, Vikram Krishnamurthy

This study presents a novel deep learning method, called GATv2-GCN, for predicting player performance in sports. To construct a dynamic player interaction graph, we leverage player statistics and their interactions during gameplay. We use a graph attention network to capture the attention that each player pays to each other, allowing for more accurate modeling of the dynamic player interactions. To handle the multivariate player statistics time series, we incorporate a temporal convolution layer, which provides the model with temporal predictive power. We evaluate the performance of our model using real-world sports data, demonstrating its effectiveness in predicting player performance. Furthermore, we explore the potential use of our model in a sports betting context, providing insights into profitable strategies that leverage our predictive power. The proposed method has the potential to advance the state-of-the-art in player performance prediction and to provide valuable insights for sports analytics and betting industries.

Dorota Pazik, Katarzyna Kosecka, Patryk Rudziński et al.

Pregnancies after kidney transplantation are considered high risk. Preconceive care is crucial for favorable mother-fetal outcome but also for good renal graft function. Herein, we report a case of kidney transplant recipient secondary to lupus nephritis with three consecutive successful pregnancies and excellent graft function after 16 post-transplant years. Preconception care included two protocolar biopsies performed prior to immunosuppressive treatment modifications. No signs of rejections were found in either biopsy, no additional treatment was necessary, and the patient was safely converted from mycophenolate mofetil to azathioprine. First pregnancy was naturally conceived, its course was uncomplicated and a healthy female newborn wasdelivered via vaginal birth. Within one year after delivery the patient presented proteinuria, borderline changes were found in the biopsy of allograft and were treated with immunosuppression augmentation and ACEI.  At 7th post implantation year, after surveillance biopsy showing no signs of rejection and appropriate pharmacotherapy adjustments, second pregnancy occurred from in vitro fertilization (IVF). It was complicated with deep vein thrombosis, intrauterine growth restriction and premature birth in 32nd week of gestation. Three months after delivery, the patient conceived spontaneously, third pregnancy course was uncomplicated. Close follow up, including protocol and indication biopsies, allowed to preserve excellent graft function in the context of multiple immunosuppressive treatment adjustments. Here we present a case where natural conception and in vitro fertilization intertwine without harming the transplanted organ.