ICMLA-camera-ready.pdf (1.14 MB)
Download file

Current advances on deep learning-based human action recognition from videos: a survey

Download (1.14 MB)
conference contribution
posted on 21.09.2021, 13:02 authored by Yixiao ZhangYixiao Zhang, Baihua Li, Hui FangHui Fang, Qinggang MengQinggang Meng
Human action recognition (HAR) from RGB videos is essential and challenging in the computer vision field due to its wide range of real-world applications in fields of human behaviour analysis, human-computer interactions, robotics and surveillance etc. Since the breakthrough and fast development of deep learning technology, the performance of HAR based on deep neural networks has been significantly improved in this decade. In this survey, we discuss the growing use of deep learning for HAR, such as representative two-stream and 3D CNNs, and particularly highlight most recent success achieved by using attention and transformers. We will provide our perspective on the new trend of designing innovative deep learning methods. In addition, we also present popular HAR datasets developed in recent years and benchmark accuracy achieved by current advancement in deep learning. This draws research attention to the challenges of HAR by identifying performance gaps when applying the deep learning methods on large HAR datasets. Further, this survey sheds light on the development of new methods and facilitates qualitative comparison with state of the art.

History

School

  • Science

Department

  • Computer Science

Published in

2021 20th IEEE International Conference On Machine Learning And Applications (ICMLA)

Pages

304 - 311

Source

20th International Conference on Machine Learning and Applications (ICMLA)

Publisher

IEEE

Version

AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

13/09/2021

Publication date

2022-01-25

Copyright date

2021

ISBN

9781665443371

Language

en

Location

Pasadena, California, U.S.A.

Event dates

13th December 2021 - 16th December 2021

Depositor

Dr Hui Fang. Deposit date: 20 September 2021