Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

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

Résumé

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.
Fichier principal
Vignette du fichier
paper2775.pdf (1007.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03958841 , version 1 (30-01-2023)

Identifiants

  • HAL Id : hal-03958841 , version 1

Citer

Pierre-Etienne Martin. Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms. MediaEval 2022 Workshop, Jan 2023, Bergen, Norway. ⟨hal-03958841⟩
3 Consultations
18 Téléchargements

Partager

Gmail Facebook X LinkedIn More