The past decade has seen a tremendous growth of interest in sports
analytics, not only from an economic and commercial perspective, but also
from a purely scientific one. In fact, there has been a growing number of
papers published at top artificial intelligence (AI) and machine learning
venues that revolve around problems in sports, as well as multiple
scientific events organized on the topic. Similar to other downstream
domains that have benefited from advances of AI and machine learning, this
growth in interest is due to important technological improvements in data
collection and processing capabilities, progress in statistical learning
and in particular deep learning, increased computational resources, and
ever-growing economic activities associated with sports and culture (e.g.,
emergent consultancy ventures revolving around sports data collection and
statistics).
The purpose of this workshop is to bring together AI researchers, sports
data scientists, and other stakeholders who are interested in the
intersection of AI and sports. In particular, we are interested in
attracting work that focuses on the overlap of multiple areas of AI such as
machine learning, game theory, and computer vision and their application to
the sports analytics domain. We also plan to have a strong list of invited
speakers, participant interaction, and panel discussions.
We seek papers that present cohesive contributions or works in progress
related to the following topics in machine learning, game theory, and/or
computer vision for sports analytics; we particularly welcome papers
targeting topics at the intersection of multiple of these fields. In terms
of application domains, papers should be focused on the analysis of sports
(e.g., football, basketball, hockey, baseball, tennis, swimming, running).
Topics of interest include, but are not limited to, the following:
-
Representation learning and aggregate statistics
-
Player and team-level statistics, vectors, and/or learned embeddings
for analysis of in-game situations
-
Modeling and learning of player/team rankings, strengths, and
weaknesses
-
Data processing, filtering, and visualisation techniques/demos
-
Evaluation of actions, trajectories and strategies, and learning of
optimal policies
-
Value estimation during in-game situations (e.g., action-values for
actions and players)
-
Detection and optimization of in-game tactics
-
Reinforcement learning for sports analytics
-
Game-theoretic and multi-agent aspects
-
Predictive and prescriptive analysis of set pieces and in-game play
-
Learning of coordination of player and team behaviors
-
Transfer and imitation learning of human play
-
Synergy or “chemistry” of groups of players
-
Physical and human factors
-
Physics-simulation of real play
-
Human factors such as injury and fatigue predictions
-
Video-based modeling
-
Event detection and activity recognition
-
Pose detection
-
Generative modeling of video data
We invite authors to submit one of two types of papers:
-
Research papers on new findings, maximum 6 pages (excluding references)
in IJCAI double column format, which will be reviewed by our program
committee and will be presented as talks and/or posters.
-
Extended abstracts summarizing previously published/submitted work, maximum
2 pages (excluding references) in IJCAI double column format. These
works will undergo a light-touch review/check by the organizing committee,
and will be presented in the poster session.
For detailed submission instructions, please see our website:
https://sites.google.com/view/ijcai-aisa-2021/call-for-papers
Important dates:
Submission: May 5, 2021, end of day (anywhere-on-earth time)
Notification: May 25, 2021
Virtual workshop: One of August 21, 22, or 23 2021 (to be confirmed soon by
IJCAI -- check back on our website closer-to!)
Best regards,
AISA Organizing Committee
_______________________________________________
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai
