Towards Active Learning for Action Spotting in Association Football Videos

Abstract

Association football is a complex and dynamic sport, with numerous actions occurring simultaneously in each game. Analyzing football videos is challenging and requires identifying subtle and diverse spatio-temporal patterns. Despite recent advances in computer vision, current algorithms still face significant challenges when learning from limited annotated data, lowering their performance in detecting these patterns. In this paper, we propose an active learning framework that selects the most informative video samples to be annotated next, thus drastically reducing the annotation effort and accelerating the training of action spotting models to reach the highest accuracy at a faster pace. Our approach leverages the notion of uncertainty sampling to select the most challenging video clips to train on next, hastening the learning process of the algorithm. We demonstrate that our proposed active learning framework effectively reduces the required training data for accurate action spotting in football videos. We achieve similar performances for action spotting with NetVLAD++ on SoccerNet-v2, using only one-third of the dataset, indicating significant capabilities for reducing annotation time and improving data efficiency. We further validate our approach on two new datasets that focus on temporally localizing actions of headers and passes, proving its effectiveness across different action semantics in football. We believe our active learning framework for action spotting would support further applications of action spotting algorithms and accelerate annotation campaigns in the sports domain.

Accepted at CVSports'23

References in corpus (8)

• Deep Bayesian Active Learning with Image Data
• Body Part-Based Representation Learning for Occluded Person Re-Identification
• SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
• DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
• Semi-Supervised Training to Improve Player and Ball Detection in Soccer
• SoccerNet 2022 Challenges Results
• A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
• Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022

Cited by in corpus (2)

• X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model
• 3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach