MuLMINet: Multi-Layer Multi-Input Transformer Network with Weighted Loss

Minwoo Seong, Jeongseok Oh, SeungJun Kim
7/17/2023
cs.AI

No official code found. Best implementation: stan5dard/IJCAI-CoachAI-Challenge-2023 (5 stars, last commit 2023-07-14).

Abstract

The increasing use of artificial intelligence (AI) technology in turn-based sports, such as badminton, has sparked significant interest in evaluating strategies through the analysis of match video data. Predicting future shots based on past ones plays a vital role in coaching and strategic planning. In this study, we present a Multi-Layer Multi-Input Transformer Network (MuLMINet) that leverages professional badminton player match data to accurately predict future shot types and area coordinates. Our approach resulted in achieving the runner-up (2nd place) in the IJCAI CoachAI Badminton Challenge 2023, Track 2. To facilitate further research, we have made our code publicly accessible online, contributing to the broader research community's knowledge and advancements in the field of AI-assisted sports analysis.

View on arXivView PDF

Code Implementations(1)

stan5dard/IJCAI-CoachAI-Challenge-2023Community100%

Badminseok

50Shell, PythonJul 6, 20233 years ago

Similar Papers

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

89% match1 repo2782023

Automated Hit-frame Detection for Badminton Match Analysis

89% match1 repo352023

Benchmarking Stroke Forecasting with Stroke-Level Badminton Dataset

84% match1 repo2782023

BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports

84% match1 repo522025

AI coach for badminton

84% match2024

Automated Tennis Player and Ball Tracking with Court Keypoints Detection (Hawk Eye System)

84% match2025

Cite this paper

@article{seong2023mulminet,
  title  = {MuLMINet: Multi-Layer Multi-Input Transformer Network with Weighted Loss},
  author = {Minwoo Seong and Jeongseok Oh and SeungJun Kim},
  year   = {2023},
  eprint = {2307.08262},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.08262v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.08262.svg)](https://codeofpaper.com/paper/2307.08262)

Discussion