13.3.12.16 Random Field Models for Structure Matching

Chapter Contents (Back)
Random Field Model. Structure Matching.

Wong, A.K.C., and Ghahraman, D.E.,
Random Graphs: Structural-Contextual Dichotomy,
PAMI(2), No. 4, July 1980, pp. 341-348. BibRef 8007

Wong, A.K.C., You, M.,
Entropy and Distance of Random Graphs with Application to Structural pattern Recognition,
PAMI(7), No. 5, September 1985, pp. 599-609. BibRef 8509
Earlier: A2, A1:
An Algorithm for Graph Optimal Isomorphism,
ICPR84(316-319). BibRef

Pelkowitz, L.,
A Continuous Relaxation Labeling Algorithm for Markov Random Fields,
SMC(20), 1990, pp. 709-715. BibRef 9000

Li, S.Z.,
Matching: Invariant to Translations, Rotations, and Scale Changes,
PR(25), No. 6, June 1992, pp. 583-594.
Elsevier DOI BibRef 9206

Li, S.Z.,
A Markov Random Field Model for Object Matching under Relational Constraints,
CVPR94(866-869).
IEEE DOI BibRef 9400
And:
Markov Random Field Models in Computer Vision,
ECCV94(B:361-370).
Springer DOI Probabilistic based graph matching approach. BibRef

Li, S.Z.,
Markov Random Field Modeling in Computer Vision,
New York: Springer-Verlag1995. 260 pp. ISBN 0-387-70145-1. Or: (US) ISBN 4-431-70145-1.
HTML Version. Or:
HTML Version. Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. Topics include: introduction to fundamental theories, formulations of MRF vision models, MRF parameter estimation, and optimization algorithms. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. BibRef 9500

Modestino, J.W., and Zhang, J.,
A Markov Random Field Model-Based Approach to Image Interpretation,
PAMI(14), No. 6, June 1992, pp. 606-615.
IEEE DOI BibRef 9206
Earlier: CVPR89(458-465).
IEEE DOI From region segmented images (
See also Model-Fitting Approach to Cluster Validation with Application to Stochastic Model-Based Image Segmentation, A. ), generate labeled regions using domain knowledge, features, and relationships. BibRef

Kumar, S.[Sanjiv], Hebert, M.[Martial],
Discriminative Random Fields,
IJCV(68), No. 2, June 2006, pp. 179-201.
Springer DOI 0606
BibRef
Earlier:
Discriminative random fields: a discriminative framework for contextual interaction in classification,
ICCV03(1150-1157).
IEEE DOI 0311
Classify regions given a single image. Model interactions with adjacent regions. BibRef

Kumar, S.[Sanjiv], August, J.[Jonas], Hebert, M.[Martial],
Exploiting Inference for Approximate Parameter Learning in Discriminative Fields: An Empirical Study,
EMMCVPR05(153-168).
Springer DOI 0601
BibRef

Liang, C.K., Cheng, C.C., Lai, Y.C., Chen, L.G., Chen, H.H.,
Hardware-Efficient Belief Propagation,
CirSysVideo(21), No. 5, May 2011, pp. 525-537.
IEEE DOI 1105
Assigning labels to the nodes of a graphical model such as the Markov random field (MRF). Reduce memory and bandwith requirements. BibRef

Sminchisescu, C.[Cristian], Welling, M.[Max],
Generalized darting Monte Carlo,
PR(44), No. 10-11, October-November 2011, pp. 2738-2748.
Elsevier DOI 1101
Markov chain Monte Carlo; Markov random fields; Darting; Constrained optimization; 3D reconstruction; Human tracking BibRef

Ladicky, L.[Lubor], Russell, C.[Chris], Kohli, P.[Pushmeet], Torr, P.H.S.[Philip H. S.],
Inference Methods for CRFs with Co-occurrence Statistics,
IJCV(103), No. 2, June 2013, pp. 213-225.
Springer DOI 1306
BibRef
Earlier:
Graph Cut Based Inference with Co-occurrence Statistics,
ECCV10(V: 239-253).
Springer DOI 1009
Award, ECCV. BibRef
Earlier:
Associative hierarchical CRFs for object class image segmentation,
ICCV09(739-746).
IEEE DOI 0909
Compute segmentations (or labellings) at different levels, pixels, segments, etc. Random field model to integrate different features. BibRef

Ladicky, L.[Lubor], Russell, C.[Chris], Kohli, P.[Pushmeet], Torr, P.H.S.[Philip H. S.],
Associative Hierarchical Random Fields,
PAMI(36), No. 6, June 2014, pp. 1056-1077.
IEEE DOI 1406
Computational modeling BibRef


Jiang, Y.[Yun], Saxena, A.,
Infinite Latent Conditional Random Fields,
PGMs13(262-266)
IEEE DOI 1403
random processes BibRef

Yu, W.[Wei], Ashraf, A.B.[Ahmed Bilal], Chang, Y.J.[Yao-Jen], Li, C.C.[Cong-Cong], Chen, T.H.[Tsu-Han],
3D augmented Markov random field for object recognition,
ICIP10(3889-3892).
IEEE DOI 1009
3D and appearance. BibRef

Flenner, A.[Arjuna],
Time dependent Markov matrices for automated image analysis,
Southwest10(193-196).
IEEE DOI 1005
SVD to encode data geometry. BibRef

Okumura, T.[Takeshi], Takiguchi, T.[Tetsuya], Ariki, Y.[Yasuo],
Generic Object Recognition by Tree Conditional Random Field Based on Hierarchical Segmentation,
ICPR10(3025-3028).
IEEE DOI 1008
BibRef

Petersen, K.[Kersten], Fehr, J.[Janis], Burkhardt, H.[Hans],
Fast Generalized Belief Propagation for MAP Estimation on 2D and 3D Grid-Like Markov Random Fields,
DAGM08(xx-yy).
Springer DOI 0806
Award, GCPR, HM. BibRef

Riviere, D., Mangin, J.F., Martinez, J.M., Tupin, F., Papadopoulos-Orfanos, D., Frouin, V.,
Relational graph labelling using learning techniques and markov random fields,
ICPR02(II: 172-175).
IEEE DOI 0211
BibRef

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
Structural Matching for Computer Vision .


Last update:Mar 16, 2024 at 20:36:19