Skip to content

Opening book details…

About this document

Wa0004. by ciyat1010 is a document available to read on EtoBox.

This paper presents a novel 3D motion image recognition model that integrates a 3D CNN with a Gated Recurrent Unit (GRU) and an attention mechanism to enhance action recognition accuracy. The proposed model effectively captures spatio-temporal features from video sequences and emphasizes key frames, achieving superior performance with accuracies of 83.2% and 87.3% in Cross-Subject and Cross-View evaluations, respectively. The study highlights the model

Author
ciyat1010
Language
EN