3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks

Renaud Péteri
Julien Morlier
  • Function : Author
  • PersonId : 1077091

Abstract

The paper addresses the problem of recognition of actions in video with low inter-class variability such as Table Tennis strokes. Two stream, "twin" convolutional neural networks are used with 3D convolutions both on RGB data and optical flow. Actions are recognized by classification of temporal windows. We introduce 3D attention modules and examine their impact on classification efficiency. In the context of the study of sportsmen performances, a corpus of the particular actions of table tennis strokes is considered. The use of attention blocks in the network speeds up the training step and improves the classification scores up to 5% with our twin model. We visualize the impact on the obtained features and notice correlation between attention and player movements and position. Score comparison of state-of-the-art action classification method and proposed approach with attentional blocks is performed on the corpus. Proposed model with attention blocks outperforms previous model without them and our baseline.
Fichier principal
Vignette du fichier
root.pdf (1.69 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02977646 , version 1 (19-11-2020)

Identifiers

Cite

Pierre-Etienne Martin, Jenny Benois-Pineau, Renaud Péteri, Julien Morlier. 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks. 25th International Conference on Pattern Recognition (ICPR2020), Jan 2021, Milano, Italy. ⟨hal-02977646⟩

Collections

CNRS
188 View
265 Download

Altmetric

Share

Gmail Facebook X LinkedIn More