A Compositional Model for Low-Dimensional Image Set Representation

被引：8

作者：

Mobahi, Hossein ^{[1
]}

Liu, Ce ^{[2
]}

Freeman, William T. ^{[1
]}

机构：

[1] MIT, Cambridge, MA 02139 USA

[2] Microsoft Res, Cambridge, MA USA

来源：

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2014年

关键词：

D O I：

10.1109/CVPR.2014.172

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Learning a low-dimensional representation of images is useful for various applications in graphics and computer vision. Existing solutions either require manually specified landmarks for corresponding points in the images, or are restricted to specific objects or shape deformations. This paper alleviates these limitations by imposing a specific model for generating images; the nested composition of color, shape, and appearance. We show that each component can be approximated by a low-dimensional subspace when the others are factored out. Our formulation allows for efficient learning and experiments show encouraging results.

引用

页码：1322 / 1329

页数：8

共 50 条

[1] Low-dimensional facial image representation using FLD and MDS
Choi, J
Yi, J
ADVANCES IN INTELLIGENT COMPUTING, PT 1, PROCEEDINGS, 2005, 3644 : 223 - 232
[2] Low-dimensional topology, low-dimensional field theory and representation theory
Fuchs, Juergen
Schweigert, Christoph
REPRESENTATION THEORY - CURRENT TRENDS AND PERSPECTIVES, 2017, : 255 - 267
[3] DEEP LOW-DIMENSIONAL SPECTRAL IMAGE REPRESENTATION FOR COMPRESSIVE SPECTRAL RECONSTRUCTION
Monroy, Brayan
Bacca, Jorge
Arguello, Henry
2021 IEEE 31ST INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2021,
[4] Spectral image destriping using a low-dimensional model
Adler-Golden, S.
Richtsmeier, S.
Conforti, P.
Bernstein, L.
ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL IMAGERY XIX, 2013, 8743
[5] Low-dimensional representation of error covariance
Tippett, MK
Cohn, SE
Todling, R
Marchesin, D
TELLUS SERIES A-DYNAMIC METEOROLOGY AND OCEANOGRAPHY, 2000, 52 (05) : 533 - 553
[6] Low-dimensional representation of genomic sequences
Richard C. Tillquist
Manuel E. Lladser
Journal of Mathematical Biology, 2019, 79 : 1 - 29
[7] Low-Dimensional Representation of Genomic Sequences
Tillquist, Richard C.
Lladser, Manuel E.
ACM-BCB'19: PROCEEDINGS OF THE 10TH ACM INTERNATIONAL CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY AND HEALTH INFORMATICS, 2019, : 549 - 549
[8] Low-dimensional representation of genomic sequences
Tillquist, Richard C.
Lladser, Manuel E.
JOURNAL OF MATHEMATICAL BIOLOGY, 2019, 79 (01) : 1 - 29
[9] Low-dimensional representation of Gaussian mixture model supervector for language recognition
Yang, Jinchao
Zhang, Xiang
Suo, Hongbin
Lu, Li
Zhang, Jianping
Yan, Yonghong
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2012, : 1 - 7
[10] Low-dimensional representation of Gaussian mixture model supervector for language recognition
Jinchao Yang
Xiang Zhang
Hongbin Suo
Li Lu
Jianping Zhang
Yonghong Yan
EURASIP Journal on Advances in Signal Processing, 2012

← 1 2 3 4 5 →