A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge

Luping Wang, Hao Guo, Bin Liu
6/9/2023
cs.CV

Official code: ZJLAB-AMMI/E2E-Spot-MBS (10 stars, MIT, last commit 2023-06-05).

Abstract

This technical report presents our solution to Ball Action Spotting in videos. Our method reached second place in the CVPR'23 SoccerNet Challenge. Details of this challenge can be found at https://www.soccer-net.org/tasks/ball-action-spotting. Our approach is developed based on a baseline model termed E2E-Spot, which was provided by the organizer of this competition. We first generated several variants of the E2E-Spot model, resulting in a candidate model set. We then proposed a strategy for selecting appropriate model members from this set and assigning an appropriate weight to each model. The aim of this strategy is to boost the performance of the resulting model ensemble. Therefore, we call our approach Boosted Model Ensembling (BME). Our code is available at https://github.com/ZJLAB-AMMI/E2E-Spot-MBS.

View on arXivView PDF

Code Implementations(1)

ZJLAB-AMMI/E2E-Spot-MBSOfficial100%
MIT

Code to implement the Runner-up Solution to the CVPR'23 SoccerNet Challenge (Ball Action Spotting Task)

102PythonJun 5, 20233 years agoMIT
ball-action-spottingensemble-learningensemble-modelfine-grainedvideo-event-recognition

Similar Papers

Widely Applicable Strong Baseline for Sports Ball Detection and Tracking

83% match1 repo1832023

ASTRA: An Action Spotting TRAnsformer for Soccer Videos

82% match1 repo452024

SoccerSynth-Detection: A Synthetic Dataset for Soccer Player Detection

82% match1 repo72025

TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos

81% match1 repo792024

Towards Active Learning for Action Spotting in Association Football Videos

81% match2023

SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines

80% match2026

Cite this paper

@article{wang2023boosted,
  title  = {A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge},
  author = {Luping Wang and Hao Guo and Bin Liu},
  year   = {2023},
  eprint = {2306.05772},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.05772v2}
}

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/2306.05772.svg)](https://codeofpaper.com/paper/2306.05772)

Discussion