Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition

TL;DR

This paper introduces MsMHA-VTN, a novel video transformer network utilizing multiscale multi-head attention for dynamic hand gesture recognition, achieving high accuracy on benchmark datasets.

Contribution

The paper proposes a multiscaled multi-head attention model within a video transformer for improved gesture recognition, incorporating multiscale feature extraction and multi-modality analysis.

Findings

Achieved 88.22% accuracy on NVGesture dataset.

Achieved 99.10% accuracy on Briareo dataset.

Demonstrated superior performance over existing methods.

Abstract

Dynamic gesture recognition is one of the challenging research areas due to variations in pose, size, and shape of the signer's hand. In this letter, Multiscaled Multi-Head Attention Video Transformer Network (MsMHA-VTN) for dynamic hand gesture recognition is proposed. A pyramidal hierarchy of multiscale features is extracted using the transformer multiscaled head attention model. The proposed model employs different attention dimensions for each head of the transformer which enables it to provide attention at the multiscale level. Further, in addition to single modality, recognition performance using multiple modalities is examined. Extensive experiments demonstrate the superior performance of the proposed MsMHA-VTN with an overall accuracy of 88.22\% and 99.10\% on NVGesture and Briareo datasets, respectively.