liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Scale coding bag-of-words for action recognition
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
Computer Vision Center, CS Department, Universitat Autonoma de Barcelona, Spain.
Computer Vision Center, CS Department, Universitat Autonoma de Barcelona, Spain.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV).ORCID iD: 0000-0002-6096-3648
2014 (English)In: Pattern Recognition (ICPR), 2014 22nd International Conference on, Institute of Electrical and Electronics Engineers Inc. , 2014, no 6976979, 1514-1519 p.Conference paper, Published paper (Refereed)
Abstract [en]

Recognizing human actions in still images is a challenging problem in computer vision due to significant amount of scale, illumination and pose variation. Given the bounding box of a person both at training and test time, the task is to classify the action associated with each bounding box in an image. Most state-of-the-art methods use the bag-of-words paradigm for action recognition. The bag-of-words framework employing a dense multi-scale grid sampling strategy is the de facto standard for feature detection. This results in a scale invariant image representation where all the features at multiple-scales are binned in a single histogram. We argue that such a scale invariant strategy is sub-optimal since it ignores the multi-scale information available with each bounding box of a person. This paper investigates alternative approaches to scale coding for action recognition in still images. We encode multi-scale information explicitly in three different histograms for small, medium and large scale visual-words. Our first approach exploits multi-scale information with respect to the image size. In our second approach, we encode multi-scale information relative to the size of the bounding box of a person instance. In each approach, the multi-scale histograms are then concatenated into a single representation for action classification. We validate our approaches on the Willow dataset which contains seven action categories: interacting with computer, photography, playing music, riding bike, riding horse, running and walking. Our results clearly suggest that the proposed scale coding approaches outperform the conventional scale invariant technique. Moreover, we show that our approach obtains promising results compared to more complex state-of-the-art methods.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2014. no 6976979, 1514-1519 p.
Series
International Conference on Pattern Recognition, ISSN 1051-4651
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:liu:diva-116804DOI: 10.1109/ICPR.2014.269ISI: 000359818001107Scopus ID: 2-s2.0-84919946713ISBN: 9781479952083 (print)OAI: oai:DiVA.org:liu-116804DiVA: diva2:801569
Conference
22nd International Conference on Pattern Recognition, ICPR 2014
Available from: 2015-04-09 Created: 2015-04-02 Last updated: 2017-03-07

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Authority records BETA

Khan, FahadFelsberg, Michael

Search in DiVA

By author/editor
Khan, FahadFelsberg, Michael
By organisation
Computer VisionThe Institute of TechnologyCenter for Medical Image Science and Visualization (CMIV)
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 333 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf