skip to main content
10.1145/3007669.3007688acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicimcsConference Proceedingsconference-collections
short-paper

Adaptively Weighted Graph Fusion for Image Retrieval

Published: 19 August 2016 Publication History

Abstract

In content-based image retrieval, feature representation is a fundamental issue and the selection of features significantly impacts the retrieval performance. Generally, the performance of a single visual feature is limited and the fusion with multiple complementary features is a preferable solution to boost the accuracy of image retrieval. In this paper, we propose an adaptively weighted graph fusion method to boost the retrieval accuracy. Given a query image, for each feature, one graph is constructed based on the nearest-neighborhood of database images. In order to evaluate the quality of this feature, we firstly use the PageRank algorithm to analyse the linked graph and get the corresponding PageRank value of each relevant image, which can be regarded as a conditional probability. Then, the weight of each feature is determined by the distribution of the above probability. We evaluate our method on two public datasets and the experimental results demonstrate that our method improves the retrieval performance consistently.

References

[1]
H. Jegou, M. Douze, and C. Schmid. Hamming embedding and weak geometric consistency for large scale image search. In ECCV, pages 304--317. 2008.
[2]
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. B. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. In ACM MM, 2014.
[3]
A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1097--1105, 2012.
[4]
Z. Liu, H. Li, W. Zhou, R. Hong, and Q. Tian. Uniting keypoints: Local visual information fusion for large-scale image search. IEEE TMM, 2015.
[5]
D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91--110, 2004.
[6]
K. Nandakumar, Y. Chen, S. C. Dass, and A. K. Jain. Likelihood ratio-based biometric score fusion. IEEE TPAMI, 30(2):342--347, 2008.
[7]
D. Nister and H. Stewenius. Scalable recognition with a vocabulary tree. In CVPR, volume 2, pages 2161--2168, 2006.
[8]
L. Page, S. Brin, R. Motwani, and T. Winograd. The pagerank citation ranking: bringing order to the web. 1999.
[9]
D. Qin, C. Wengert, and L. Van Gool. Query adaptive similarity for large scale object retrieval. In CVPR, pages 1610--1617, 2013.
[10]
S. Sun, W. Zhou, Q. Tian, and H. Li. Scalable object retrieval with compact image representation from generic object regions. ACM TOMM, 2016.
[11]
J. Xiao, W. Zhou, and Q. Tian. Exploring tag relevance for image tag re-ranking. In ACM SIGIR, pages 1069--1070, 2012.
[12]
L. Xie, Q. Tian, W. Zhou, and B. Zhang. Heterogeneous graph propagation for large-scale web image search. IEEE TIP, 24(11):4287--4298, 2015.
[13]
L. Zhang and Y. Rui. Image search-from thousands to billions in 20 years. ACM TOMM, 9(1s):36, 2013.
[14]
S. Zhang, M. Yang, T. Cour, K. Yu, and D. N. Metaxas. Query specific rank fusion for image retrieval. IEEE TPAMI, 37(4):803--815, 2015.
[15]
S. Zhang, M. Yang, X. Wang, Y. Lin, and Q. Tian. Semantic-aware co-indexing for image retrieval. In ICCV, pages 1673--1680, 2013.
[16]
L. Zheng, S. Wang, Z. Liu, and Q. Tian. Lp-norm idf for large scale image search. In CVPR, pages 1626--1633, 2013.
[17]
W. Zhou, H. Li, R. Hong, Y. Lu, and Q. Tian. BSIFT: Toward data-independent codebook for large scale image search. IEEE TIP, 24(3):967--979, 2015.
[18]
W. Zhou, M. Yang, H. Li, X. Wang, Y. Lin, and Q. Tian. Towards codebook-free: Scalable cascaded hashing for mobile image search. IEEE TMM, 16(3):601--611, 2014.

Cited By

View all
  • (2023)TsP-Tran: Two-Stage Pure Transformer for Multi-Label Image RetrievalProceedings of the 2023 ACM International Conference on Multimedia Retrieval10.1145/3591106.3592269(425-433)Online publication date: 12-Jun-2023
  • (2023)Link-Driven Study to Enhance Text-Based Image Retrieval: Implicit Links Versus Explicit LinksIEEE Access10.1109/ACCESS.2023.330746411(90526-90537)Online publication date: 2023
  • (2019)Uncovering Hidden Links Between Images Through Their Textual ContextEnterprise Information Systems10.1007/978-3-030-26169-6_18(370-395)Online publication date: 28-Jul-2019

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and Service
August 2016
360 pages
ISBN:9781450348508
DOI:10.1145/3007669
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

  • Xidian University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 August 2016

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Image retrieval
  2. PageRank algorithm
  3. adaptive weight
  4. graph fusion
  5. nearest-neighborhood

Qualifiers

  • Short-paper
  • Research
  • Refereed limited

Conference

ICIMCS'16

Acceptance Rates

ICIMCS'16 Paper Acceptance Rate 77 of 118 submissions, 65%;
Overall Acceptance Rate 163 of 456 submissions, 36%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)1
  • Downloads (Last 6 weeks)0
Reflects downloads up to 20 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2023)TsP-Tran: Two-Stage Pure Transformer for Multi-Label Image RetrievalProceedings of the 2023 ACM International Conference on Multimedia Retrieval10.1145/3591106.3592269(425-433)Online publication date: 12-Jun-2023
  • (2023)Link-Driven Study to Enhance Text-Based Image Retrieval: Implicit Links Versus Explicit LinksIEEE Access10.1109/ACCESS.2023.330746411(90526-90537)Online publication date: 2023
  • (2019)Uncovering Hidden Links Between Images Through Their Textual ContextEnterprise Information Systems10.1007/978-3-030-26169-6_18(370-395)Online publication date: 28-Jul-2019

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media