short-paper

Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors

Authors:

Filip Radenović,

Ondrej ChumAuthors Info & Claims

ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

Pages 587 - 590

https://doi.org/10.1145/2671188.2749366

Published: 22 June 2015 Publication History

Abstract

This paper addresses the construction of a short-vector (128D) image representation for large-scale image and particular object retrieval. In particular, the method of joint dimensionality reduction of multiple vocabularies is considered. We study a variety of vocabulary generation techniques: different k-means initializations, different descriptor transformations, different measurement regions for descriptor extraction. Our extensive evaluation shows that different combinations of vocabularies, each partitioning the descriptor space in a different yet complementary manner, results in a significant performance improvement, which exceeds the state-of-the-art.

References

[1]

R. Arandjelovic and A. Zisserman. Three things everyone should know to improve object retrieval. In Proc. CVPR, pages 2911--2918, 2012.

Digital Library

[2]

R. Arandjelović and A. Zisserman. All about VLAD. In Proc. CVPR, 2013.

Digital Library

[3]

O. Chum and J. Matas. Unsupervised discovery of co-occurrence in sparse high dimensional data. In Proc. CVPR, 2010.

[4]

O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman. Total recall: Automatic query expansion with a generative feature model for object retrieval. In Proc. ICCV, 2007.

[5]

P. Comon. Independent component analysis, a new concept? Signal processing, 36(3):287--314, 1994.

Digital Library

[6]

H. Jégou and O. Chum. Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening. In Proc. ECCV, Firenze, Italy, Oct. 2012.

Digital Library

[7]

H. Jégou, M. Douze, and C. Schmid. On the burstiness of visual elements. In Proc. CVPR, 2009.

[8]

H. Jégou, M. Douze, and C. Schmid. Improving bag-of-features for large scale image search. IJCV, 87(3):316--336, 2010.

Digital Library

[9]

H. Jégou, M. Douze, and C. Schmid. Product quantization for nearest neighbor search. IEEE PAMI, 33(1):117--128, 2011.

Digital Library

[10]

H. Jégou, F. Perronnin, M. Douze, J. Sánchez, P. Pérez, and C. Schmid. Aggregating local image descriptors into compact codes. IEEE PAMI, 34(9):1704--1716, 2012.

Digital Library

[11]

H. Jégou, A. Zisserman, et al. Triangulation embedding and democratic aggregation for image search. In Proc. CVPR, 2014.

Digital Library

[12]

D. G. Lowe. Distinctive image features from scale-invariant keypoints. Proc. ICCV, 60(2):91--110, 2004.

Digital Library

[13]

J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proc. BMVC, volume 1, pages 384--393, 2002.

[14]

K. Mikolajczyk and C. Schmid. Scale & affine invariant interest point detectors. IJCV, 1(60):63--86, 2004.

Digital Library

[15]

A. Mikulik, M. Perd'och, O. Chum, and J. Matas. Learning vocabularies over a fine quantization. IJCV, pages 1--13, 2012.

Digital Library

[16]

D. Nister and H. Stewenius. Scalable recognition with a vocabulary tree. In Proc. CVPR, 2006.

Digital Library

[17]

A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3):145--175, 2001.

Digital Library

[18]

M. Perdoch, O. Chum, and J. Matas. Efficient representation of local geometry for large scale object retrieval. In Proc. CVPR, 2009.

[19]

F. Perronnin, Y. Liu, J. Sanchez, and H. Poirier. Large-scale image retrieval with compressed fisher vectors. In Proc. CVPR, 2010.

[20]

J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. In Proc. CVPR, 2007.

[21]

J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman. Lost in quantization: Improving particular object retrieval in largescale image databases. In Proc. CVPR, 2008.

[22]

F. Radenovic, H. Jegou, and O. Chum. Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors - Extended Version. ArXiv e-prints, Apr. 2015.

[23]

J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In Proc. ICCV, pages 1470--1477, 2003.

Digital Library

[24]

A. Torralba, R. Fergus, and Y. Weiss. Small codes and large image databases for recognition. In Proc. CVPR, pages 1--8. IEEE, 2008.

[25]

T. Tuytelaars and L. Van Gool. Wide baseline stereo matching based on local, affinely invariant regions. In Proc. BMVC, 2000.

[26]

Y. Weiss, A. Torralba, and R. Fergus. Spectral hashing. In Proc. NIPS, pages 1753--1760, 2009.

Digital Library

Cited By

Suma PKordopatis-Zilos GIscen ATolias G(2024)AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level RetrievalComputer Vision – ECCV 202410.1007/978-3-031-73202-7_18(307-325)Online publication date: 21-Nov-2024
https://doi.org/10.1007/978-3-031-73202-7_18
Wei BJia RFu SLyu XGao LTang Z(2022)MIR: A Benchmark for Molecular Image Retrival with a Cross-modal Pretraining Framework2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM55620.2022.9995641(3902-3904)Online publication date: 6-Dec-2022
https://doi.org/10.1109/BIBM55620.2022.9995641
Krishna TMcGuinness KO'Connor NCheng WKankanhalli MWang MChu WLiu JWorring M(2021)Evaluating Contrastive Models for Instance-based Image RetrievalProceedings of the 2021 International Conference on Multimedia Retrieval10.1145/3460426.3463585(471-475)Online publication date: 24-Aug-2021
https://dl.acm.org/doi/10.1145/3460426.3463585
Show More Cited By

Index Terms

Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors
1. Information systems
  1. Information retrieval
    1. Retrieval models and ranking

Recommendations

Comparative Study on Dimensionality Reduction in Large-Scale Image Retrieval
ISM '13: Proceedings of the 2013 IEEE International Symposium on Multimedia

Dimensionality reduction plays a significant role for the performance of large-scale image retrieval. In this paper, various dimensionality reduction methods are compared to validate their own performance in image retrieval. For this purpose, first, the ...
Multi-feature Image Retrieval by Nonlinear Dimensionality Reduction
ISCID '14: Proceedings of the 2014 Seventh International Symposium on Computational Intelligence and Design - Volume 02

Multi-feature fusion is effective in raising the matching performance of image retrieval. However, the "Curse of Dimensionality" has to be solved. Traditional dimensionality reduction methods cannot reflect the high-order correlation among features and ...
Moments discriminant analysis for supervised dimensionality reduction

Most of the well-known supervised dimensionality reduction methods assume unimodal or Gaussian likelihoods, which may not be appropriate in the real life applications. In this manuscript, we introduce a novel supervised dimensionality reduction approach,...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

June 2015

700 pages

ISBN:9781450332743

DOI:10.1145/2671188

General Chairs:
Alex Hauptmann
Carnegie Mellon University, USA
,
Chong-Wah Ngo
City University of Hong Kong, China
,
Xiangyang Xue
Fudan University, China
,
Program Chairs:
Yu-Gang Jiang
Fudan University, China
,
Cees Snoek
University of Amsterdam and Qualcomm Research Netherlands
,
Nuno Vasconcelos
University of California, San Diego, USA

Copyright © 2015 ACM.

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]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 June 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

Conference

ICMR '15

Sponsor:

SIGMM

ICMR '15: International Conference on Multimedia Retrieval

June 23 - 26, 2015

Shanghai, China

Acceptance Rates

ICMR '15 Paper Acceptance Rate 48 of 127 submissions, 38%;

Overall Acceptance Rate 254 of 830 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

19
Total Citations
View Citations
113
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Suma PKordopatis-Zilos GIscen ATolias G(2024)AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level RetrievalComputer Vision – ECCV 202410.1007/978-3-031-73202-7_18(307-325)Online publication date: 21-Nov-2024
https://doi.org/10.1007/978-3-031-73202-7_18
Wei BJia RFu SLyu XGao LTang Z(2022)MIR: A Benchmark for Molecular Image Retrival with a Cross-modal Pretraining Framework2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)10.1109/BIBM55620.2022.9995641(3902-3904)Online publication date: 6-Dec-2022
https://doi.org/10.1109/BIBM55620.2022.9995641
Krishna TMcGuinness KO'Connor NCheng WKankanhalli MWang MChu WLiu JWorring M(2021)Evaluating Contrastive Models for Instance-based Image RetrievalProceedings of the 2021 International Conference on Multimedia Retrieval10.1145/3460426.3463585(471-475)Online publication date: 24-Aug-2021
https://dl.acm.org/doi/10.1145/3460426.3463585
Mahmoud AKaramti HHadjouni M(2020)A hybrid late fusion-genetic algorithm approach for enhancing CBIR performanceMultimedia Tools and Applications10.1007/s11042-020-08825-679:27-28(20281-20298)Online publication date: 1-Jul-2020
https://dl.acm.org/doi/10.1007/s11042-020-08825-6
Fan LZhao HZhao HLiu PHu H(2019)Image Retrieval Based on Learning to Rank and Multiple LossISPRS International Journal of Geo-Information10.3390/ijgi80903938:9(393)Online publication date: 4-Sep-2019
https://doi.org/10.3390/ijgi8090393
Radenovic FTolias GChum O(2019)Fine-Tuning CNN Image Retrieval with No Human AnnotationIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2018.284656641:7(1655-1668)Online publication date: 1-Jul-2019
https://doi.org/10.1109/TPAMI.2018.2846566
Raza MQamar URaza MQamar U(2019)BackgroundUnderstanding and Using Rough Set Based Feature Selection: Concepts, Techniques and Applications10.1007/978-981-32-9166-9_2(27-51)Online publication date: 24-Aug-2019
https://doi.org/10.1007/978-981-32-9166-9_2
Liu PMiao ZGuo HWang YAi N(2018)Adding spatial distribution clue to aggregated vector in image retrievalEURASIP Journal on Image and Video Processing10.1186/s13640-018-0247-02018:1Online publication date: 7-Feb-2018
https://doi.org/10.1186/s13640-018-0247-0
Zhang X(2018)Near-Duplicate Image Retrieval Based on Multiple Features2018 IEEE Visual Communications and Image Processing (VCIP)10.1109/VCIP.2018.8698664(1-4)Online publication date: Dec-2018
https://doi.org/10.1109/VCIP.2018.8698664
Zheng LYang YTian Q(2018)SIFT Meets CNN: A Decade Survey of Instance RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2017.270974940:5(1224-1244)Online publication date: 1-May-2018
https://doi.org/10.1109/TPAMI.2017.2709749
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents