Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Bilinear programming for human activity recognition with unknown MRF graphs|
Van Den Hengel, A.
|Citation:||Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 1690-1697|
|Publisher Place:||United States of America|
|Series/Report no.:||IEEE Conference on Computer Vision and Pattern Recognition|
|Conference Name:||IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)|
|Zhenhua Wang, Qinfeng Shi, Chunhua Shen and Anton van den Hengel|
|Abstract:||Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty. However, the underlying graph structure is often manually specified, or automatically constructed by heuristics. We show, instead, that learning an MRF graph and performing MAP inference can be achieved simultaneously by solving a bilinear program. Equipped with the bilinear program based MAP inference for an unknown graph, we show how to estimate parameters efficiently and effectively with a latent structural SVM. We apply our techniques to predict sport moves (such as serve, volley in tennis) and human activity in TV episodes (such as kiss, hug and Hi-Five). Experimental results show the proposed method outperforms the state-of-the-art.|
|Keywords:||Human activity recognition; MRF; bilinear programming, linear programming|
|Appears in Collections:||Computer Science publications|
Files in This Item:
|hdl_77411.pdf||Accepted version||2.78 MB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.