English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The paper addresses the problem of recognition of actions in video with lowinter-class variability such as Table Tennis strokes. Two stream, "twin"convolutional neural networks are used with 3D convolutions both on RGB dataand optical flow. Actions are recognized by classification of temporal windows.We introduce 3D attention modules and examine their impact on classificationefficiency. In the context of the study of sportsmen performances, a corpus ofthe particular actions of table tennis strokes is considered. The use ofattention blocks in the network speeds up the training step and improves theclassification scores up to 5% with our twin model. We visualize the impact onthe obtained features and notice correlation between attention and playermovements and position. Score comparison of state-of-the-art actionclassification method and proposed approach with attentional blocks isperformed on the corpus. Proposed model with attention blocks outperformsprevious model without them and our baseline.

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