A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Wu, Fei; Wang, Qingzhong; Bian, Jiang; Ding, Ning; Lu, Feixiang; Cheng, Jiang; Dou, Dejing; Xiong, Haoyi

doi:10.1109/tmm.2022.3232034

Cited by 38 publications

(12 citation statements)

References 207 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [81] introduced a video-text recognition framework that uses the natural language of vision-language models (VLMs), such as CLIP [25] to bridge the video domain for cross-modal knowledge extraction. With LLMs or VLMs as guidance, human action and object recognition methods have been widely applied to video surveillance [86], robotic navigation [78], [87], [88], medical diagnosis and healthcare [89], sports [86]. For instance, LLMs with vision sensors enable robots with stronger NLP capacity based on the video sequences.…”

Section: B Video Scene Understandingmentioning

confidence: 99%

A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming

Zhou,

Wang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper offers an insightful examination of how currently top-trending AI technologies, i.e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming. It highlights the innovative use of these technologies in producing highly realistic videos, a significant leap in bridging the gap between real-world dynamics and digital creation. The study also delves into the advanced capabilities of LLMs in video understanding, demonstrating their effectiveness in extracting meaningful information from visual content, thereby enhancing our interaction with videos. In the realm of video streaming, the paper discusses how LLMs contribute to more efficient and user-centric streaming experiences, adapting content delivery to individual viewer preferences. This comprehensive review navigates through the current achievements, ongoing challenges, and future possibilities of applying Generative AI and LLMs to video-related tasks, underscoring the immense potential these technologies hold for advancing the field of video technology related to multimedia, networking, and AI communities.Impact Statement-This paper contributes to the field of video technology by examining the integration of Generative AI and Large Language Models (LLMs) in video generation, understanding, and streaming. Its exploration of these technologies offers a foundational understanding of their potential and limitations in enhancing the realism and interactivity of video content. The exploration of LLMs in video comprehension sets the stage for advancements in accessibility and interaction, promising enhanced educational tools, improved user interfaces, and advanced video analytics applications. Additionally, the paper underscores the role of LLMs in optimizing video streaming services, leading to more personalized and bandwidth-efficient platforms. This could substantially benefit the entertainment sector with adaptive streaming solutions tailored to individual preferences. By identifying key challenges and future research directions, the paper guides ongoing efforts to merge AI with video technology, while raising awareness about potential ethical issues. Its influence extends beyond academia, encouraging responsible AI development and policy-making in video technology, balancing technological advancements with ethical considerations.

show abstract

Section: B Video Scene Understandingmentioning

confidence: 99%

A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming

Zhou,

Wang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…A significant number of studies carried out result from the acquisition of images and videos, in part, due to technological developments in this area [13,14]. Evolution does not always result in positive outcomes, as the enhanced image and video quality of modern devices can make it challenging to capture well-balanced images and videos due to their increased sensitivity to brightness and color variations in the environment [15].…”

Section: Studies On Performance Analysis In Sportmentioning

confidence: 99%

User Assessment of a Customized Taekwondo Athlete Performance Cyber–Physical System

Cunha,

Barbosa,

Ferreira

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This study outlines the assessment of the cyber–physical system SPERTA, which was designed to evaluate the real-time performance of Taekwondo athletes. The system conducts performance analyses focusing on speed, acceleration, strength, and identifying and quantifying the athlete’s movements. The research involved administering an online questionnaire to athletes and coaches to evaluate the system’s acceptance and usability. The methodology included using a questionnaire with open and closed questions to assess participant satisfaction and system usability. The results showed a positive response to the system, with participants emphasizing its reliability and ease of use. An analysis of the responses revealed a strong internal consistency, as indicated by the Cronbach’s alpha coefficient, which enhances the research instrument’s reliability. Additionally, the analysis of open-ended questions was conducted through thematic analysis to gain a deeper understanding of participants’ experiences and perceptions of the system. These results highlight the effectiveness of the SPERTA system as a valuable tool for the real-time performance evaluation of Taekwondo athletes, providing insights for future improvements and the development of more effective training techniques.

show abstract

“…A way to select specific tactics is to watch videos and understand in which way opponents "implement" specific tactics (e.g., offensive vs. defensive). In this context, it is important to analyse videos with regard to different behavioral patterns of opponents and thus to better support game tactics preparation for a team [133]. Tsai et al [124] address to problem of tactic recognition in basketball videos.…”

Section: Tactics Against Opponentsmentioning

confidence: 99%

Sports Recommender Systems: Overview and Research Issues

Felfernig,

Wundara,

Tran

et al. 2023

Preprint

View full text Add to dashboard Cite

Sports recommender systems receive an increasing attention due to their potential of fostering healthy living, improving personal well-being, and increasing performances in sport. These systems support people in sports, for example, by the recommendation of healthy and performance-boosting food items, the recommendation of training practices, talent and team recommendation, and the recommendation of specific tactics in competitions. With applications in the virtual world, for example, the recommendation of maps or opponents in e-sports, these systems already transcend conventional sports scenarios where physical presence is needed. On the basis of different working examples, we present an overview of sports recommender systems applications and techniques. Overall, we analyze the related state-of-the-art and discuss open research issues.

show abstract

A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications

Cited by 38 publications

References 207 publications

A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming

A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming

User Assessment of a Customized Taekwondo Athlete Performance Cyber–Physical System

Sports Recommender Systems: Overview and Research Issues

Contact Info

Product

Resources

About