Human Activity Recognition

Lukas Hedegaard Morsing*, Negar Heidari, Alexandros Iosifidis

*Corresponding author for this work

Research output: Contribution to book/anthology/report/proceedingBook chapterResearchpeer-review

Abstract

With the increasing amount of videos available on the internet and in security settings, human activity recognition has become a highly important topic in machine learning. In this chapter, we cover the topic of deep learning for human activity recognition and the tasks of trimmed action recognition, temporal action localization, and spatiotemporal action localization. Throughout our treatise, we discuss different architectural building blocks including 2D Convolutional Neural Networks (CNNs), 3D-CNNs, Recursive Neural Networks (RNNs), and Spatial-Temporal Graph Convolution Networks (ST-GCNs), and how they were used in state-if-the-art models for human activity recognition. Moreover, we discuss how multiple modalities and data resolutions can be fused via a multistream network topology, and how video-classification models can be extended for usage in (spatio)temporal action localization. Finally, we provide a curated list of data sets for human activity recognition tasks.
Original languageEnglish
Title of host publicationDeep Learning for Robot Perception and Cognition
EditorsAlexandros Iosifidis, Anastasios Tefas
Number of pages30
PublisherElsevier
Publication date2022
Pages341-370
Chapter14
ISBN (Electronic)9780323857871
DOIs
Publication statusPublished - 2022

Keywords

  • 3D convolutional neural network
  • Human activity recognition
  • Spatial-temporal graph convolution network
  • Spatiotemporal localization
  • Video classification

Fingerprint

Dive into the research topics of 'Human Activity Recognition'. Together they form a unique fingerprint.

Cite this