iccv iccv2013 iccv2013-445 iccv2013-445-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Cheng Deng, Rongrong Ji, Wei Liu, Dacheng Tao, Xinbo Gao
Abstract: Visual reranking has been widely deployed to refine the quality of conventional content-based image retrieval engines. The current trend lies in employing a crowd of retrieved results stemming from multiple feature modalities to boost the overall performance of visual reranking. However, a major challenge pertaining to current reranking methods is how to take full advantage of the complementary property of distinct feature modalities. Given a query image and one feature modality, a regular visual reranking framework treats the top-ranked images as pseudo positive instances which are inevitably noisy, difficult to reveal this complementary property, and thus lead to inferior ranking performance. This paper proposes a novel image reranking approach by introducing a Co-Regularized Multi-Graph Learning (Co-RMGL) framework, in which the intra-graph and inter-graph constraints are simultaneously imposed to encode affinities in a single graph and consistency across different graphs. Moreover, weakly supervised learning driven by image attributes is performed to denoise the pseudo- labeled instances, thereby highlighting the unique strength of individual feature modality. Meanwhile, such learning can yield a few anchors in graphs that vitally enable the alignment and fusion of multiple graphs. As a result, an edge weight matrix learned from the fused graph automatically gives the ordering to the initially retrieved results. We evaluate our approach on four benchmark image retrieval datasets, demonstrating a significant performance gain over the state-of-the-arts.
[1] W. Hsu and L. Kennedy and S.-F. Chang. Reranking methods for visual search.
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9] IEEE Multimedia, 2007 W. Liu and Y. Jiang and J. Luo and S.-F. Chang Noise resistant graph ranking for improved web image search. CVPR, 2011. X. Tian and D. Tao and X.-S. Hua and X. Wu. Active reranking for web image search. IEEE TIP, 2010. V. Jain and M. Varma. Learning to re-rank: Query-dependent image reranking using click data. WWW, 2011. O. Chum and A. Mikul ´ık and A. Perd’och and J. Matas. Total recall II: Query expansion revisited. CVPR, 201 1. X. Wang and K. Liu and X. Tang. Query-specific visual semantic spaces for web image re-ranking. CVPR, 2011. J. Krapac and M. Allan and J. Verbeek and F. Juried. Improving web image search results using query-relative classifiers. CVPR, 2010. J. Lu and J. Zhou and J. Wang and T. Mei and X.-S. Hua and S. Li. Image search results refinement via outlier detection using deep contexts. CVPR, 2012. S. Zhang and M. Yang and T. Cour and K. Yu and D. N. Metaxas. Query specific fusion for image retrieval. ECCV, 2012. 2606 Co-RMGL+AM (third row in each query) on Oxford, INRIA and Paris (red rectangle indicates the irrelevance images with the query, and green rectangle represents part of learned graph anchors. The last column lists some important attributes mined by our proposed WSAS).
[10] D. Crandall and D. Huttenlocher. Weakly supervised learning of part-based spatial models for visual object recognition. ECCV, 2006.
[11] R. Fergus and P. Perona and A. Zisserman. Weakly supervised scale-invariant learning of models for visual recognition. IJCV, 2007.
[12] A. Mikul ´ık and M. Perd’och and O. Chum and J. Matas. Learning a fine vocabulary. ECCV, 2010.
[13] D. Qin and S. Gammeter and L. Bossard and T. Quack and L. VanGool. Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. CVPR, 2011.
[14] J. Liu and W. Lai and X.-S. Hua and Y. Huang, and S. Li. Video search reranking via multi-graph propogation. ACM MM, 2007.
[15] M. Wang and H. Li and D. Tao and K. Lu and X. Wu Multimodal graph-based reranking for web image search. IEEE TIP, 2012.
[16] V. Ferrari and A. Zisserman. Learning visual attributes. NIPS, 2007.
[17] A. Farhadi and I. Endres and D. Hoiem and D. Forsyth. Describing objects by their attributes. CVPR, 2009.
[18] N. Kumar and A. C. Berg and P. N. Belhumeur and S. K. Nayar. Attribute and simile classifiers for face verification. ICCV, 2009.
[19] D. Parikh and K. Grauman. Relative Attributes. ICCV, 2011.
[20] C. Lampert and H. Nickisch and S. Harmeling. Learning to detect unseen object classes by between-class attribute transfer. CVPR, 2009.
[21] M. Douze and A. Ramisa and C. Schmid Combining attributes ans Fisher vectors for efficient image retrieval CVPR, 2011.
[22] D. Parikh and K. Grauman. Interactively building a discriminative vocabulary of nameable attributes. CVPR, 2011.
[23] T. Berg and A. Berg and J. Shih. Automatic attribute discovery and characterization from noisy web data. ECCV, 2010.
[24] M. Pandey and S. Lazebnik. Scene recognition and weakly supervised object localization with deformable part-based models. ICCV, 2011.
[25] A. Vezhnevets and V. Ferrari and J. M. Buhmann. Weakly supervised semantic segmentation with a multi-image model. ICCV, 2011.
[26] S. Roweis and L. Saul. Nonlinear dimensionality reduction by locally linear embedding. Science, 2000.
[27] A. Beck and M. Teboulle. A fast iterative shrinkage thresholding algorithm for linear inverse problems. SIAM J. Image Science, 2009.
[28] X. Chen and Q. Lin and S. Kim and J. Carbonell and E. Xing Smoothing proximal gradient method for general structured sparse regression. Ann. Appl. Stat., 2012.
[29] W. Liu and J. He and S.-F. Chang. Large graph construction for scalable semisupervised learning. ICML, 2010.
[30] L. Torresani and M. Szummer and A. Fitzgibbon. Efficient object category recognition using classemes. ECCV, 2010. [3 1] L.-J. Li and H. Su and E. P. Xing and L. Fei-Fei. Object Bank: A high-level
[32]
[33]
[34]
[35]
[36]
[37]
[38] image representation for scene classification & semantic feature sparsification. NIPS, 2010. T. Agrawal and R. Srikant. Fast algorithms for mining association rules in large databases. VLDB, 1994. J. Philbin and O. Chum and M. Isard and J. Sivic and A. Zisserman. Object retrieval with large vocabularies and fast spatial matching. CVPR, 2007. J. Philbin and O. Chum and M. Isard and J. Sivic and A. Zisserman. Lost in quantization: Improving particular object retrieval in large scale image databases. CVPR, 2008. H. J e´gou and M. Douze and C. Schmid. Hamming embedding and weak geometry consistency for large scale image search. ECCV, 2008. D. Nist e´r and H. Stew e´nius. Scalable recognition with a vocabulary tree. CVPR, 2006. S. Lazebnik and C. Schmid and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognition natural scene categories. CVPR, 2006. A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envalope. IJCV, 2001 . 2607