Transformer neural networks for human activity recognition

Date

2022

Journal Title

Journal ISSN

Volume Title

Publisher

Kansas State University

Abstract

Human activity recognition is an emerging and important area in computer vision which seeks to determine the activity an individual or group of individuals are performing. The applications of this field ranges from generating highlight videos in sports, to intelligent surveillance and gesture recognition. Most activity recognition systems rely on a combination of convolutional neural networks (CNNs) to perform feature extraction from the data and recurrent neural networks (RNNs) to determine the time dependent nature of the data. This paper proposes and designs two transformer neural networks for human activity recognition: a recurrent transformer, a specialized neural network used to make predictions on sequences of data, as well as a vision transformer, a transformer optimized for extracting salient features from images, to improve speed and scalability of activity recognition. We have provided an extensive comparison of the proposed transformer neural networks with the contemporary CNN and RNN-based human activity recognition models in terms of speed and accuracy.

Description

Keywords

Transformer, Recurrent transformer, Vision transformer, Human activity recognition, Computer vision, Machine learning

Graduation Month

August

Degree

Master of Science

Department

Department of Computer Science

Major Professor

Arslan Munir

Date

Type

Thesis

Citation