Change search
ReferencesLink to record
Permanent link

Direct link
Coloring Action Recognition in Still Images
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. (Computer Vision Laboratory)
Computer vision Center Barcelona, Universitat Autonoma de Barcelona, Spain.
Computer vision Center Barcelona, Universitat Autonoma de Barcelona, Spain.
Media Integration and Communication Center, University of Florence, Florence, Italy.
Show others and affiliations
2013 (English)In: International Journal of Computer Vision, ISSN 0920-5691, E-ISSN 1573-1405, Vol. 105, no 3, 205-221 p.Article in journal (Refereed) Published
Abstract [en]

In this article we investigate the problem of human action recognition in static images. By action recognition we intend a class of problems which includes both action classification and action detection (i.e. simultaneous localization and classification). Bag-of-words image representations yield promising results for action classification, and deformable part models perform very well object detection. The representations for action recognition typically use only shape cues and ignore color information. Inspired by the recent success of color in image classification and object detection, we investigate the potential of color for action classification and detection in static images. We perform a comprehensive evaluation of color descriptors and fusion approaches for action recognition. Experiments were conducted on the three datasets most used for benchmarking action recognition in still images: Willow, PASCAL VOC 2010 and Stanford-40. Our experiments demonstrate that incorporating color information considerably improves recognition performance, and that a descriptor based on color names outperforms pure color descriptors. Our experiments demonstrate that late fusion of color and shape information outperforms other approaches on action recognition. Finally, we show that the different color–shape fusion approaches result in complementary information and combining them yields state-of-the-art performance for action classification.

Place, publisher, year, edition, pages
2013. Vol. 105, no 3, 205-221 p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-97463DOI: 10.1007/s11263-013-0633-0ISI: 000323659900002OAI: diva2:647854
Collaborative Unmanned AerialSystems, CUAS (within the Linnaeus environment CADICS), ELLIIT, the Strategic Area for ICT research, funded by the Swedish Government
eLLIIT - The Linköping‐Lund Initiative on IT and Mobile CommunicationsICT - The Next Generation
Available from: 2013-09-12 Created: 2013-09-12 Last updated: 2016-05-04Bibliographically approved

Open Access in DiVA

fulltext(7092 kB)532 downloads
File information
File name FULLTEXT01.pdfFile size 7092 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Khan, Fahad ShahbazFelsberg, Michael
By organisation
Computer VisionThe Institute of TechnologyCenter for Medical Image Science and Visualization (CMIV)
In the same journal
International Journal of Computer Vision
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 532 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 533 hits
ReferencesLink to record
Permanent link

Direct link