Enhancing human action recognition with region proposals

Fahimeh Rezazadegan, Sareh Shirazi, Niko Sünderhauf, Michael Milford, Ben Upcroft

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

1 Citation (Scopus)


Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an "action region proposal" method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-The-Art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-The-Art in spatio-Temporally fused action recognition performance.

Original languageEnglish
Title of host publicationACRA 2015
Subtitle of host publicationAustralasian Conference on Robotics and Automation 2015
PublisherAustralian Robotics and Automation Association
Number of pages6
ISBN (Electronic)9780980740462
Publication statusPublished - 2015
Externally publishedYes
Event2015 Australasian Conference on Robotics and Automation, ACRA 2015 - Canberra, Australia
Duration: 2 Dec 20154 Dec 2015

Publication series

NameAustralasian Conference on Robotics and Automation, ACRA
ISSN (Print)1448-2053


Conference2015 Australasian Conference on Robotics and Automation, ACRA 2015


Dive into the research topics of 'Enhancing human action recognition with region proposals'. Together they form a unique fingerprint.

Cite this