Article

Co-transduction for shape retrieval

Authors:

Zhuowen TuAuthors Info & Claims

ECCV'10: Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III

Pages 328 - 341

Published: 05 September 2010 Publication History

Abstract

In this paper, we propose a new shape/object retrieval algorithm, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). Different types of measures may focus on different aspects of the objects: e.g. measures computed based on contours and skeletons are often complementary to each other. Our goal is to develop an algorithm to fuse different similarity measures for robust shape retrieval through a semi-supervised learning framework. We name our method co-transduction which is inspired by the co-training algorithm [1]. Given two similarity measures and a query shape, the algorithm iteratively retrieves the most similar shapes using one measure and assigns them to a pool for the other measure to do a re-ranking, and vice-versa. Using co-transduction, we achieved a significantly improved result of 97.72% on the MPEG-7 dataset [2] over the state-of-the-art performances (91% in [3], 93.4% in [4]). Our algorithm is general and it works directly on any given similarity measures/metrics; it is not limited to object shape retrieval and can be applied to other tasks for ranking/retrieval.

References

[1]

Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proc. of COLT, pp. 92-100 (1998)

Digital Library

[2]

Latecki, L., Lakámper, R., Eckhardt, U.: Shape descriptors for non-rigid shapes with a single closed contour. In: Proc. of CVPR, pp. 424-429 (2000)

[3]

Yang, X., Bai, X., Latecki, L., Tu, Z.: Improving shape retrieval by learning graph transduction. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 788-801. Springer, Heidelberg (2008)

[4]

Kontschieder, P., Donoser, M., Bischof, H.: Beyond pairwise shape similarity analysis. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) Computer Vision - ACCV 2009. LNCS, vol. 5996. Springer, Heidelberg (2010)

Digital Library

[5]

Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. PAMI 24, 522-705 (2002)

Digital Library

[6]

Ling, H., Jacobs, D.: Shape classification using the inner-distance. IEEE Trans. PAMI 29, 286-299 (2007)

Digital Library

[7]

Sebastian, T.B., Klein, P.N., Kimia, B.B.: Recognition of shapes by editing their shock graphs. IEEE Trans. PAMI 25, 116-125 (2004)

Digital Library

[8]

Zhu, X.: Semi-supervised learning with graphs. In: Doctoral Dissertation, Carnegie Mellon University, CMU-LTI-05-192 (2005)

[9]

Yang, X., Koknar-Tezel, S., Latecki, L.: Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval. In: Proc. of CVPR (2009)

[10]

Zhou, Z.H., Li, M.: Semi-supervised regression with co-training. In: Proc. of IJCAI (2004)

Digital Library

[11]

Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J. of Machine Learning Research 7, 2399-2434 (2006)

Digital Library

[12]

Wang, W., Zhou, Z.H.: Analyzing co-training style algorithms. In: Kok, J.N., et al. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 454-465. Springer, Heidelberg (2007)

Digital Library

[13]

Coifman, R., Lafon, S.: Diffusion maps. Applied and Comp. Harmonic Ana. (2006)

[14]

Aslan, C., Erdem, A., Erdem, E., Tari, S.: Disconnected skeleton: Shape at its absolute scale. IEEE Trans. PAMI 30, 2188-2201 (2008)

Digital Library

[15]

Wei, C.H., Li, Y., Chau, W.Y., Li, C.T.: Trademark image retrieval using synthetic features for describing global shape and interior structure. Pattern Recognition 42, 386-394 (2009)

Digital Library

[16]

Tu, Z., Yuille, A.L.: Shape matching and recognition - using generative models and informative features. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 195-209. Springer, Heidelberg (2004)

[17]

Schmidt, F.R., Toeppe, E., Cremers, D.: Efficient planar graph cuts with applications in computer vision. In: Proc. of CVPR (2009)

[18]

Felzenszwalb, P.F., Schwartz, J.: Hierarchical matching of deformable shapes. In: CVPR (2007)

[19]

Xu, C., Liu, J., Tang, X.: 2d shape matching by contour flexibility. IEEE Trans. PAMI 31, 180-186 (2009)

Digital Library

[20]

Egozi, A., Keller, Y., Guterman, H.: Improving shape retrieval by spectral matching and meta similarity. IEEE Trans. Image Processing 19, 1319-1327 (2010)

Digital Library

[21]

Gonzalez, R., Woods, R., Eddins, S.: Digital image processing using matlab. Prentice-Hall, EnglewoodCliffs (2004)

Digital Library

[22]

Kim, Y.S., Kim, W.Y.: Content-based trademark retrieval system using a visually salient feature. Image and Vision Computing 16, 931-939 (1998)

[23]

Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: Proc. CVPR, pp. 2161-2168 (2006)

Digital Library

[24]

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

Digital Library

[25]

Jegou, H., Schmid, C., Harzallah, H., Verbeek, J.: Accurate image search using the contextual dissimilarity measure. IEEE Trans. PAMI 32, 2-11 (2010)

Digital Library

[26]

Stewénius, H., Nistér, D.: Object recognition benchmark, http://vis.uky.edu/%7Estewe/ukbench/

[27]

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

Digital Library

[28]

Lowe, D.: Distinctive image features from scale-invariant key points. IJCV 60, 91- 110 (2004)

Digital Library

[29]

Bai, X., Yang, X., Latecki, L., Liu, W., Tu, Z.: Learning context sensitive shape similarity by graph transduction. IEEE Trans. PAMI 32, 861-874 (2010)

Digital Library

Cited By

Valem LOliveira CPedronette DAlmeida J(2018)Unsupervised Similarity Learning through Rank Correlation and kNN SetsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/324105314:4(1-23)Online publication date: 23-Oct-2018
https://dl.acm.org/doi/10.1145/3241053
Pedronette DTorres R(2016)A correlation graph approach for unsupervised manifold learning in image retrieval tasksNeurocomputing10.1016/j.neucom.2016.03.081208:C(66-79)Online publication date: 5-Oct-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.03.081
Pedronette DTorres R(2016)Combining re-ranking and rank aggregation methods for image retrievalMultimedia Tools and Applications10.1007/s11042-015-3044-075:15(9121-9144)Online publication date: 1-Aug-2016
https://dl.acm.org/doi/10.1007/s11042-015-3044-0
Show More Cited By

Co-transduction for shape retrieval
1. Computing methodologies

Recommendations

Co-Transduction for Shape Retrieval

In this paper, we propose a new shape/object retrieval algorithm, namely, co-transduction. The performance of a retrieval system is critically decided by the accuracy of adopted similarity measures (distances or metrics). In shape/object retrieval, ...
Learning Context-Sensitive Shape Similarity by Graph Transduction

Shape similarity and shape retrieval are very important topics in computer vision. The recent progress in this domain has been mostly driven by designing smart shape descriptors for providing better similarity measure between pairs of shapes. In this ...
Part-based shape retrieval
MULTIMEDIA '05: Proceedings of the 13th annual ACM international conference on Multimedia

This paper introduces a measure for computing the dissimilarity between multiple polylines and a polygon based on the turning function, and describes a part-based retrieval system using that dissimilarity measure. This dissimilarity can be efficiently ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ECCV'10: Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III

September 2010

803 pages

ISBN:364215557X

Editors:
Kostas Daniilidis
GRASP Laboratory, University of Pennsylvania, Philadelphia, PA
,
Petros Maragos
National Technical University of Athens, School of Electrical and Computer Engineering, Athens, Greece
,
Nikos Paragios
Ecole Centrale de Paris, Department of Applied Mathematics, Chatenay-Malabry, France

Sponsors

Google Inc.
Microsoft Research: Microsoft Research
technicolor
INRIA: Institut Natl de Recherche en Info et en Automatique
IBM: IBM

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 05 September 2010

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 10 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Valem LOliveira CPedronette DAlmeida J(2018)Unsupervised Similarity Learning through Rank Correlation and kNN SetsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/324105314:4(1-23)Online publication date: 23-Oct-2018
https://dl.acm.org/doi/10.1145/3241053
Pedronette DTorres R(2016)A correlation graph approach for unsupervised manifold learning in image retrieval tasksNeurocomputing10.1016/j.neucom.2016.03.081208:C(66-79)Online publication date: 5-Oct-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.03.081
Pedronette DTorres R(2016)Combining re-ranking and rank aggregation methods for image retrievalMultimedia Tools and Applications10.1007/s11042-015-3044-075:15(9121-9144)Online publication date: 1-Aug-2016
https://dl.acm.org/doi/10.1007/s11042-015-3044-0
Valem LPedronette DTorres RBorin EAlmeida JHauptmann ANgo CXue XJiang YSnoek CVasconcelos N(2015)Effective, Efficient, and Scalable Unsupervised Distance Learning in Image Retrieval TasksProceedings of the 5th ACM on International Conference on Multimedia Retrieval10.1145/2671188.2749336(51-58)Online publication date: 22-Jun-2015
https://dl.acm.org/doi/10.1145/2671188.2749336
Okada CPedronette Dda S. Torres RHauptmann ANgo CXue XJiang YSnoek CVasconcelos N(2015)Unsupervised Distance Learning by Rank Correlation Measures for Image RetrievalProceedings of the 5th ACM on International Conference on Multimedia Retrieval10.1145/2671188.2749335(331-338)Online publication date: 22-Jun-2015
https://dl.acm.org/doi/10.1145/2671188.2749335
Pedronette DPenatti OCalumby Rda S. Torres RKankanhalli MRueger SManmatha RJose Jvan Rijsbergen K(2014)Unsupervised Distance Learning By Reciprocal kNN Distance for Image RetrievalProceedings of International Conference on Multimedia Retrieval10.1145/2578726.2578770(345-352)Online publication date: 1-Apr-2014
https://dl.acm.org/doi/10.1145/2578726.2578770
Pedronette DDa Silva Torres RCalumby R(2014)Using contextual spaces for image re-ranking and rank aggregationMultimedia Tools and Applications10.1007/s11042-012-1115-z69:3(689-716)Online publication date: 1-Apr-2014
https://dl.acm.org/doi/10.1007/s11042-012-1115-z
Pedronette DDa S. Torres R(2013)Image re-ranking and rank aggregation based on similarity of ranked listsPattern Recognition10.1016/j.patcog.2013.01.00446:8(2350-2360)Online publication date: 1-Aug-2013
https://dl.acm.org/doi/10.1016/j.patcog.2013.01.004
Pedronette DTorres R(2011)Image re-ranking and rank aggregation based on similarity of ranked listsProceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I10.5555/2033460.2033515(369-376)Online publication date: 29-Aug-2011
https://dl.acm.org/doi/10.5555/2033460.2033515
Pedronette Dda S. Torres RDe Natale FDel Bimbo AHanjalic AManjunath BSatoh S(2011)Exploiting contextual spaces for image re-ranking and rank aggregationProceedings of the 1st ACM International Conference on Multimedia Retrieval10.1145/1991996.1992009(1-8)Online publication date: 18-Apr-2011
https://dl.acm.org/doi/10.1145/1991996.1992009
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents