Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms

TL;DR

This paper introduces a baseline method using 3D CNNs with attention mechanisms for sports video classification and detection tasks in MediaEval 2022, providing a publicly available benchmark.

Contribution

The paper presents two novel 3D-CNN architectures with attention mechanisms tailored for stroke classification and detection in sports videos, serving as a baseline for the MediaEval 2022 challenge.

Findings

Achieved 86.4% accuracy on classification subtask

Reached 0.131 mAP and 0.515 IoU on detection subtask

Provided publicly available baseline models for the community

Abstract

This paper presents the baseline method proposed for the Sports Video task part of the MediaEval 2022 benchmark. This task proposes two subtasks: stroke classification from trimmed videos, and stroke detection from untrimmed videos. This baseline addresses both subtasks. We propose two types of 3D-CNN architectures to solve the two subtasks. Both 3D-CNNs use Spatio-temporal convolutions and attention mechanisms. The architectures and the training process are tailored to solve the addressed subtask. This baseline method is shared publicly online to help the participants in their investigation and alleviate eventually some aspects of the task such as video processing, training method, evaluation and submission routine. The baseline method reaches 86.4% of accuracy with our v2 model for the classification subtask. For the detection subtask, the baseline reaches a mAP of 0.131 and IoU of 0.515 with our v1 model.