Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Who is doing what? Simultaneous recognition of actions and actors

: Cheema, Muhammad Shahzad; Eweiwiy, Abdalrahman; Bauckhage, Christian

Preprint urn:nbn:de:0011-n-2249730 (754 KByte PDF)
MD5 Fingerprint: 12e6e610e2bf0e0c29a635128f68c5d3
© 2012 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 17.1.2013

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society:
19th IEEE International Conference on Image Processing, ICIP 2012. Vol.1 : Lake Buena Vista, Orlando, Florida, USA, 30 September - 3 October 2012; proceedings
Piscataway/NJ: IEEE, 2012
ISBN: 978-1-4673-2534-9 (Print)
ISBN: 978-1-4673-2533-2
ISBN: 978-1-4673-2532-5 (Online)
International Conference on Image Processing (ICIP) <19, 2012, Orlando/Fla.>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()
action recognition; bilinear models; motion history volumes; expectation maximization

Recognizing human actions in videos has become a rapidly growing area of research. Most existing research has focused only on a single aspect i.e. recognition of actions. However, humans tend to perform different actions in their own styles. In this paper, we deal with the problem of simultaneously identifying actions and the underlying styles (actors) in videos. We propose a hierarchical approach based on conventional action recognition and asymmetric bilinear modeling. Our approach is solely based on dynamics of the underlying activity. Results on the multi-actor multi-action data set IXMAS show a high recognition rate.