Abstract
Most large scale image retrieval systems are based on Bag-of-Visual-Words (BoV). Typically, no spatial information about the visual words is used despite the ambiguity of visual words. To address this problem, we introduce a spatial weighting framework for BoV to encode spatial information inspired by Geometry-preserving Visual Phrases (GVP). We first interpret GVP method using this framework. We reveal that GVP gives too large spatial weighting when calculating L2-norm for images due to its implicit assumption of the independence of co-occurring GVPs. This makes GVP sensitive to images with small number of visual words. Then we propose an improved practial spatial weighting for BoV (PSW-BoV) to alleviate this effect while keep the efficiency. Experiments on Oxford 5K and MIR Flickr 1M show that PSW-BoV is robust to images with small number of visual words, and also improves the general retrieval accuracy.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Zhang, Z., Jia, Z., Chen, T.: Image Retrieval with Geometry-Preserving Visual Phrases. In: CVPR 2011, pp. 809–816. IEEE Computer Society, Colorado Spings (2011)
Cao, Y., Wang, C., Li, Z., Zhang, L., Zhang, L.: Spatial Bag-of-Features. In: CVPR 2010, pp. 3352–3359. IEEE Computer Society, San Francisco (2010)
Sivic, J., Zisserman, A.: Video google: A Text Retrieval Approach to Object Matching in Videos. In: ICCV 2003, pp. 1470–1477. IEEE Computer Society, Nice (2003)
Nister, D., Stewenius, H.: Scalable Recognition with A Vocabulary Tree. In: CVPR 2006, pp. 2161–2168. IEEE Computer Society, New York (2006)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object Retrieval with Large Vocabularies and Fast Spatial Matching. In: CVPR 2007, pp. 1–8. IEEE Computer Society, Minneapolis (2007)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases. In: CVPR 2008, pp. 1–8. IEEE Computer Society, Anchorage (2008)
Jegou, H., Douze, M., Schmid, C.: Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: CVPR 2006, pp. 2169–2178. IEEE Computer Society, New York (2006)
Mikolajczyk, K., Schmid, C.: Scale & Affine Invariant Interest Point Detectors. International Journal of Computer Vision 60, 63–86 (2004)
Lowe, D.: Distinctive Image Features From Scale-Invariant Interest Point Detectors. International Journal of Computer Vision 60, 91–110 (2004)
Huiskes, M., Thomee, B., Lew, M.: New Trends and Ideas in Visual Concept Detection. In: ACM MIR 2010, pp. 527–536. ACM, Pennsylvania (2010)
Marszalek, M., Schmid, C.: Spatial Weighting for Bag-of-Features. In: CVPR 2006, pp. 2118–2125. IEEE Computer Society, New York (2006)
Chen, X., Hu, X., Shen, X.: Spatial Weighting for Bag-of-Visual-Words and Its Application in Content-Based Image Retrieval. In: Theeramunkong, T., Kijsirikul, B., Cercone, N., Ho, T.-B. (eds.) PAKDD 2009. LNCS, vol. 5476, pp. 867–874. Springer, Heidelberg (2009)
Martinet, J., Urruty, T., Djeraba, C.: A new spatial weighting scheme for bag-of-visual-words. In: CBMI 2010, Grenoble, France, pp. 1–6 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, F., Wang, H., Li, H., Zhang, S. (2013). Large Scale Image Retrieval with Practical Spatial Weighting for Bag-of-Visual-Words. In: Li, S., et al. Advances in Multimedia Modeling. MMM 2013. Lecture Notes in Computer Science, vol 7732. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35725-1_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-35725-1_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35724-4
Online ISBN: 978-3-642-35725-1
eBook Packages: Computer ScienceComputer Science (R0)