VisuaLeague: Player performance analysis using spatial-temporal data

Afonso, Ana Paula; Carmo, Maria Beatriz; Gonçalves, Tiago; Vieira, Pedro

doi:10.1007/s11042-019-07952-z

Cited by 23 publications

(14 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first area in which these results have implications is in the domain of computational support for esports. A great number of computational tools for esports exist, which broadly provide players with assistance in decision making (Chen et al, 2018a , b ; Christiansen et al, 2019 ; Eger and Sauma Chacón, 2020 ) and review of gameplay (Wallner and Kriglstein, 2016 , 2020 ; Kuan et al, 2017 ; Afonso et al, 2019 ). These tools are often explicitly motivated by the desire to help players learn and master their game.…”

Section: Discussionmentioning

confidence: 99%

“…Specifically, SRL skills, such as goal setting, can have an impact on gameplay performance. In the context of esports, knowledge of the role and impact of SRL would be invaluable to helping players more effectively learn and gain expertise, which is often cited as the primary motivation for the development of computational support tools for esports (Wallner and Kriglstein, 2016 ; Kuan et al, 2017 ; Afonso et al, 2019 ).…”

Section: Related Workmentioning

confidence: 99%

“…There are several ways that the formal study of SRL in esports could benefit both the learning and games communities. For games, and especially for esports, knowledge of how SRL manifests within the domain could highlight opportunities to more effectively support learning through specialized training or computational tools that target SRL processes (Kuan et al, 2017 ; Afonso et al, 2019 ). Further, knowledge of where SRL processes are not being leveraged by players, or where they differ across skill levels, may highlight elements of the gameplay experience where learning is more difficult.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

“Because I'm Bad at the Game!” A Microanalytic Study of Self Regulated Learning in League of Legends

2021

View full text Add to dashboard Cite

Self-regulated learning (SRL) is a form of learning guided by the student's own meta-cognition, motivation, and strategic action, often in the absence of an educator. The use of SRL processes and skills has been demonstrated across numerous academic and non-academic contexts including athletics. However, manifestation of these processes within esports has not been studied. Similar to traditional athletes, esports players' performance is likely correlated with their ability to engage SRL skills as they train. Thus, the study of SRL in the context of esports would be valuable in supporting players' learning and mastery of play through specialized training and computational support. Further, an understanding of how SRL manifests in esports would highlight new opportunities to use esports in education. Existing work on SRL in games, however, predominantly focuses on educational games. In this work, we aim to take a first step in the study of SRL in esports by replicating Kitsantas and Zimmerman's (2002) volleyball study in the context of League of Legends. We compared the self-regulatory processes of expert, non-expert, and novice League of Legends players, and found that there were significant differences for processes in the forethought phase. We discuss three implications of these findings: what they mean for the development of future computational tools for esports players, implications that esports may be able to teach SRL skills that transfer to academics, and what educational technology can learn from esports to create more effective tools.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

“Because I'm Bad at the Game!” A Microanalytic Study of Self Regulated Learning in League of Legends

2021

View full text Add to dashboard Cite

show abstract

“…Object detection is one of the fundamental tasks in computer vision and form the basis of many high level tasks including but not limited to object tracking [1][2][3][4][5][6][7][8][9] sports player performance analysis [10][11][12], crowd analysis [13][14][15][16], crowd counting [13,13,17,18], action recognition [19][20][21][22], anomaly detection [23][24][25][26], detection based facial emotion recognition [27,28], pose estimation [29,30], video scene understanding [31][32][33]. Technically, object detection is defined as given an image or video, find if there is an instance or instances of the object of interest present.…”

Section: Introductionmentioning

confidence: 99%

YOLOv2 for Pigs Detection in Industrial Farming

Khan¹,

Khan²

2020

Preprint

View full text Add to dashboard Cite

Generic object detection is one of the most important and flourishing branches of computer vision and has real-life applications in our day to day life. With the exponential development of deep learning-based techniques for object detection, the performance has enhanced considerably over the last 2 decades. However, due to the data-hungry nature of deep models, they don't perform well on tasks which have very limited labeled dataset available. To handle this problem, we proposed a transfer learning-based deep learning approach for detecting multiple pigs in the indoor farm setting. The approach is based on YOLO-v2 and the initial parameters are used as the optimal starting values for train-ing the network. Compared to the original YOLO-v2, we transformed the detector to detect only one class of objects i.e. pigs and the back-ground. For training the network, the farm-specific data is annotated with the bounding boxes enclosing pigs in the top view. Experiments are performed on a different configuration of the pen in the farm and convincing results have been achieved while using a few hundred annotated frames for fine-tuning the network.

show abstract

“…Afonso and et.al. [1] explore analytics in video games by using visualizations techniques, in particular animated maps, for control and analysis of spatio-temporal information data associated to player performance within game environment.…”

mentioning

confidence: 99%

Special issue on information visualisation

Francese

Banissi

Risi

2019

Multimed Tools Appl

View full text Add to dashboard Cite

We are in the Big Data era, characterized by an increasing amount of information generated everyday by all the phenomena concerning our life. These data are collected by many information sources and systems ranging from IoT sensors, large databases, social networks and interactive platforms, as well as generic media like images, videos and audios. Thus, to be able to comprehend the phenomena underlying this data there is the need of designing effective visualization tools. The papers selected for this special issue outline and evaluate some recent works on multimedia tools for information visualization and interaction with various types of data, including textual documents, graphs, spatio-temporal data, multimedia contents, and musical data. The international conference on information Visualisation (iV), one of the longest running on the subject has open forum philosophy of interdisciplinary drive to define its subject theme and discussion and focus group. This special issue of Multimedia Tools and Applications for Information Visualisation is based on the handful of submissions to the 22 nd International Conference on Information Visualisation (iV18), which was held in Italy in July 2018. The selected papers give examples of techniques, domains and number of case studies to address some issues. The papers presented in this Special Issue investigate different aspects of the theme highlighted above. The first set of papers [1, 2, 12, 16] investigate and evaluate the visualization of spatial, temporal and spatio-temporal data. Almeida et al. [2] consider how and why consideration of Level of Detail (LoD) plays a crucial role in analytics. They propose a Visual Analytics approach-VAST, allows users to simultaneous inspection of phenomenon using different LoDs. VAST demonstrates using LoDs will reveal different prospective and hence portraying different perception of the phenomenon.

show abstract

VisuaLeague: Player performance analysis using spatial-temporal data

Cited by 23 publications

References 36 publications

“Because I'm Bad at the Game!” A Microanalytic Study of Self Regulated Learning in League of Legends

“Because I'm Bad at the Game!” A Microanalytic Study of Self Regulated Learning in League of Legends

YOLOv2 for Pigs Detection in Industrial Farming

Special issue on information visualisation

Contact Info

Product

Resources

About