caa a22 4500 606159371 CHVBK 20210128100624.0 cr unu---uuuuu 210128e20151001xx s 000 0 eng 10.1007/s00521-014-1810-y doi (NATIONALLICENCE)springer-10.1007/s00521-014-1810-y Multimedia event detection with ℓ2-regularized logistic Gaussian mixture regression [Elektronische Daten] [Changyu Liu, Shoubin Dong, Bin Lu, Mohamed Abdel-Mottaleb] Multimedia event detection (MED) is one of the most important branches of multimedia content analysis. Current research work on MED focuses mainly on detecting specific events, such as sport events, news events and suspicious events, which is far from achieving a complicated and generic MED due to the fact that these events usually contain a lot of visual attributes, such as objects, scenes and human actions. Being different from visual features, visual attributes are hidden classes to event detectors and event classifiers. Hence, proper representation of these visual attributes could be helpful in building a sophisticated and generic MED. In this paper, we use Gaussian mixture model (GMM) for representing video events with the motivation that the individual component densities of GMM could model some underlying hidden visual attributes and propose a ℓ2-regularized logistic Gaussian mixture regression approach, which is also called LLGMM classifier, for a more generic and complicated MED. We also propose an efficient iterative algorithm, which uses gradient descent, a standard convex optimization method, to solve the objective function of LLGMM. Finally, extensive experiments are conducted on the challenging TRECVID MED 2012 development dataset. The results demonstrate the effectiveness of the proposed LLGMM classifier for MED. The Natural Computing Applications Forum, 2015 Multimedia event detection nationallicence ℓ2 Regularization nationallicence Logistic regression nationallicence Gaussian mixture model nationallicence LLGMM classifier nationallicence Liu Changyu School of Computer Science and Engineering, South China University of Technology, 510006, Guangzhou, China aut Dong Shoubin School of Computer Science and Engineering, South China University of Technology, 510006, Guangzhou, China aut Lu Bin School of Computer Science, Wuyi University, 529020, Jiangmen, China aut Abdel-Mottaleb Mohamed Department of Electrical and Computer Engineering, University of Miami, 33146, Coral Gables, FL, USA aut Neural Computing and Applications Springer London 26/7(2015-10-01), 1561-1574 0941-0643 26:7<1561 2015 26 521 https://doi.org/10.1007/s00521-014-1810-y text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1810-y text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Liu Changyu School of Computer Science and Engineering, South China University of Technology, 510006, Guangzhou, China aut NATIONALLICENCE 700 1- Dong Shoubin School of Computer Science and Engineering, South China University of Technology, 510006, Guangzhou, China aut NATIONALLICENCE 700 1- Lu Bin School of Computer Science, Wuyi University, 529020, Jiangmen, China aut NATIONALLICENCE 700 1- Abdel-Mottaleb Mohamed Department of Electrical and Computer Engineering, University of Miami, 33146, Coral Gables, FL, USA aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/7(2015-10-01), 1561-1574 0941-0643 26:7<1561 2015 26 521