Home > Research > Publications & Outputs > Match graph construction for large image databases
View graph of relations

Match graph construction for large image databases

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Match graph construction for large image databases. / Kim, Kwang In; Tompkin, James; Theobald, Martin; Kautz, Jan; Theobalt, Christian.

Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I. Springer, 2012. p. 272-285 (Lecture Notes in Computer Science; Vol. 7572).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Kim, KI, Tompkin, J, Theobald, M, Kautz, J & Theobalt, C 2012, Match graph construction for large image databases. in Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I. Lecture Notes in Computer Science, vol. 7572, Springer, pp. 272-285. https://doi.org/10.1007/978-3-642-33718-5_20

APA

Kim, K. I., Tompkin, J., Theobald, M., Kautz, J., & Theobalt, C. (2012). Match graph construction for large image databases. In Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I (pp. 272-285). (Lecture Notes in Computer Science; Vol. 7572). Springer. https://doi.org/10.1007/978-3-642-33718-5_20

Vancouver

Kim KI, Tompkin J, Theobald M, Kautz J, Theobalt C. Match graph construction for large image databases. In Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I. Springer. 2012. p. 272-285. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-33718-5_20

Author

Kim, Kwang In ; Tompkin, James ; Theobald, Martin ; Kautz, Jan ; Theobalt, Christian. / Match graph construction for large image databases. Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I. Springer, 2012. pp. 272-285 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{c83e54a00ca04806bb996dc2a79ee8de,
title = "Match graph construction for large image databases",
abstract = "How best to efficiently establish correspondence among a large set of images or video frames is an interesting unanswered question. For large databases, the high computational cost of performing pair-wise image matching is a major problem. However, for many applications, images are inherently sparsely connected, and so current techniques try to correctly estimate small potentially matching subsets of databases upon which to perform expensive pair-wise matching. Our contribution is to pose the identification of potential matches as a link prediction problem in an image correspondence graph, and to propose an effective algorithm to solve this problem. Our algorithm facilitates incremental image matching: initially, the match graph is very sparse, but it becomes dense as we alternate between link prediction and verification. We demonstrate the effectiveness of our algorithm by comparing it with several existing alternatives on large-scale databases. Our resulting match graph is useful for many different applications. As an example, we show the benefits of our graph construction method to a label propagation application which propagates user-provided sparse object labels to other instances of that object in large image collections.",
keywords = "Image matching, graph construction, link prediction",
author = "Kim, {Kwang In} and James Tompkin and Martin Theobald and Jan Kautz and Christian Theobalt",
year = "2012",
doi = "10.1007/978-3-642-33718-5_20",
language = "English",
isbn = "9783642337178",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "272--285",
booktitle = "Computer Vision – ECCV 2012",

}

RIS

TY - GEN

T1 - Match graph construction for large image databases

AU - Kim, Kwang In

AU - Tompkin, James

AU - Theobald, Martin

AU - Kautz, Jan

AU - Theobalt, Christian

PY - 2012

Y1 - 2012

N2 - How best to efficiently establish correspondence among a large set of images or video frames is an interesting unanswered question. For large databases, the high computational cost of performing pair-wise image matching is a major problem. However, for many applications, images are inherently sparsely connected, and so current techniques try to correctly estimate small potentially matching subsets of databases upon which to perform expensive pair-wise matching. Our contribution is to pose the identification of potential matches as a link prediction problem in an image correspondence graph, and to propose an effective algorithm to solve this problem. Our algorithm facilitates incremental image matching: initially, the match graph is very sparse, but it becomes dense as we alternate between link prediction and verification. We demonstrate the effectiveness of our algorithm by comparing it with several existing alternatives on large-scale databases. Our resulting match graph is useful for many different applications. As an example, we show the benefits of our graph construction method to a label propagation application which propagates user-provided sparse object labels to other instances of that object in large image collections.

AB - How best to efficiently establish correspondence among a large set of images or video frames is an interesting unanswered question. For large databases, the high computational cost of performing pair-wise image matching is a major problem. However, for many applications, images are inherently sparsely connected, and so current techniques try to correctly estimate small potentially matching subsets of databases upon which to perform expensive pair-wise matching. Our contribution is to pose the identification of potential matches as a link prediction problem in an image correspondence graph, and to propose an effective algorithm to solve this problem. Our algorithm facilitates incremental image matching: initially, the match graph is very sparse, but it becomes dense as we alternate between link prediction and verification. We demonstrate the effectiveness of our algorithm by comparing it with several existing alternatives on large-scale databases. Our resulting match graph is useful for many different applications. As an example, we show the benefits of our graph construction method to a label propagation application which propagates user-provided sparse object labels to other instances of that object in large image collections.

KW - Image matching

KW - graph construction

KW - link prediction

U2 - 10.1007/978-3-642-33718-5_20

DO - 10.1007/978-3-642-33718-5_20

M3 - Conference contribution/Paper

SN - 9783642337178

T3 - Lecture Notes in Computer Science

SP - 272

EP - 285

BT - Computer Vision – ECCV 2012

PB - Springer

ER -