Match!

Auto-context modeling using multiple Kernel learning

Published on Sep 1, 2016 in ICIP (International Conference on Image Processing)
· DOI :10.1109/ICIP.2016.7532682
Huan Song4
Estimated H-index: 4
(ASU: Arizona State University),
Jayaraman J. Thiagarajan14
Estimated H-index: 14
(LLNL: Lawrence Livermore National Laboratory)
+ 1 AuthorsAndreas Spanias28
Estimated H-index: 28
(ASU: Arizona State University)
Abstract
In complex visual recognition systems, feature fusion has become crucial to discriminate between a large number of classes. In particular, fusing high-level context information with image appearance models can be effective in object/scene recognition. To this end, we develop an auto-context modeling approach under the RKHS (Reproducing Kernel Hilbert Space) setting, wherein a series of supervised learners are used to approximate the context model. By posing the problem of fusing the context and appearance models using multiple kernel learning, we develop a computationally tractable solution to this challenging problem. Furthermore, we propose to use the marginal probabilities from a kernel SVM classifier to construct the auto-context kernel. In addition to providing better regularization to the learning problem, our approach leads to improved recognition performance in comparison to using only the image features.
  • References (20)
  • Citations (2)
References20
Newest
Mar 1, 2016 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Huan Songg (ASU: Arizona State University)H-Index: 1
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last.Pavan Turaga (ASU: Arizona State University)H-Index: 24
view all 5 authors...
5 CitationsSource
#1Jayaraman J. Thiagarajan (ASU: Arizona State University)H-Index: 14
#2Karthikeyan Natesan Ramamurthy (ASU: Arizona State University)H-Index: 14
Last.Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 3 authors...
52 CitationsSource
May 1, 2014 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Po-Sen Huang (UIUC: University of Illinois at Urbana–Champaign)H-Index: 11
#2Haim Avron (IBM)H-Index: 17
Last.Bhuvana Ramabhadran (IBM)H-Index: 34
view all 5 authors...
73 CitationsSource
#1Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last.Andreas SpaniasH-Index: 28
view all 4 authors...
14 Citations
1 CitationsSource
Jun 1, 2012 in CVPR (Computer Vision and Pattern Recognition)
#1Basura Fernando (Katholieke Universiteit Leuven)H-Index: 25
#2Elisa Fromont (CNRS: Centre national de la recherche scientifique)H-Index: 13
Last.Marc Sebban (CNRS: Centre national de la recherche scientifique)H-Index: 19
view all 4 authors...
57 CitationsSource
#1Yi-Ren Yeh (CIT: Center for Information Technology)H-Index: 13
#2Ting-Chu Lin (CIT: Center for Information Technology)H-Index: 3
Last.Yu-Chiang Frank Wang (CIT: Center for Information Technology)H-Index: 24
view all 4 authors...
46 CitationsSource
#1Chih-Chung Chang (NTU: National Taiwan University)H-Index: 7
#2Lin Chih-Jen (NTU: National Taiwan University)H-Index: 57
30.8k CitationsSource
#1Mehmet Gönen (Boğaziçi University)H-Index: 14
#2Ethem Alpaydin (Boğaziçi University)H-Index: 27
1,078 Citations
Sep 1, 2009 in ICCV (International Conference on Computer Vision)
#1Peter V. Gehler (MPG: Max Planck Society)H-Index: 30
#2Sebastian Nowozin (MPG: Max Planck Society)H-Index: 37
671 CitationsSource
Cited By2
Newest
Mar 1, 2017 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Huan Song (ASU: Arizona State University)H-Index: 4
#2Jayaraman J. Thiagarajan (LLNL: Lawrence Livermore National Laboratory)H-Index: 14
Last.Andreas Spanias (ASU: Arizona State University)H-Index: 28
view all 5 authors...
8 CitationsSource
View next paperIntegrating multi-features by multiple kernel learning to better classify images