Abstract
Discovering knowledge from social images available on social network services (SNSs) is in the spotlight. For example, objects that appear frequently in images shot around a certain city may represent its characteristics (local culture, etc.) and may become the valuable sightseeing resources for people from other countries or cities. However, due to the diverse quality of social images, it is still not easy to discover such common objects from them with the conventional object discovery methods. In this paper, we propose a novel unsupervised ranking method of predicted object bounding boxes for discovering common objects from a mixed-class and noisy image dataset. Extensive experiments on standard and extended benchmarks demonstrate the effectiveness of our proposed approach. We also show the usefulness of our method with a real application in which a city’s characteristics (i.e., culture elements) are discovered from a set of images collected there.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Without loss of generality, hereafter, we generalize social image dataset as a set of mixed-class and noisy images.
- 2.
- 3.
References
Zhuang, C., Ma, Q., Liang, X., Yoshikawa, M.: Discovering obscure sightseeing spots by analysis of geo-tagged social images. In: ASONAM (2015)
Zhuang, C., Ma, Q., Yoshikawa, M.: SNS user classification and its application to obscure POI discovery. MTA 76(4), 5461–5487 (2016)
Shen, Y., Ge, M., Zhuang, C., Ma, Q.: Sightseeing value estimation by analyzing geosocial images. In: BigMM (2016)
Doersch, C., Singh, S., Gupta, A., Sivic, J., Efros, A.: What makes Paris look like Paris? TOG 31(4) (2012)
Cho, M., Kwak, S., Schmid, C., Ponce, J.: Unsupervised object discovery and localization in the wild: part-based matching with bottom-up region proposals. In: CVPR (2015)
Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images. In: CVPR (2013)
Tang, K., Joulin, A., Li, L.J., Fei-Fei, L.: Co-localization in real-world images. In: CVPR (2014)
Vahdat, A., Mori, G.: Handling uncertain tags in visual recognition. In: ICCV (2013)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)
Girshick, R.: Fast R-CNN. In: ICCV (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346–361. Springer, Cham (2014). doi:10.1007/978-3-319-10578-9_23
Kwak, S., Cho, M., Laptev, I., Ponce, J., Schmid, C.: Unsupervised object discovery and tracking in video collections. In: ICCV (2015)
Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. TPAMI 34(11), 2189–2202 (2012)
Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. NIPS 1(2), 5 (2006)
Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 73–86. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33709-3_6
Manen, S., Guillaumin, M., Van Gool, L.: Prime object proposals with randomized prim’s algorithm. In: ICCV (2013)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2007 (VOC 2007) results. In: Citeseer (2007)
Torralba, A., Fergus, R., Weiss, Y.: Small codes and large image databases for recognition. In: CVPR (2008)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Acknowledgement
This work is partly supported by JSPS KAKENHI (16K12532) and MIC SCOPE (172307001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ge, M., Zhuang, C., Ma, Q. (2017). A Ranking Based Approach for Robust Object Discovery from Images of Mixed Classes. In: Sung, WK., et al. Information Retrieval Technology. AIRS 2017. Lecture Notes in Computer Science(), vol 10648. Springer, Cham. https://doi.org/10.1007/978-3-319-70145-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-70145-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70144-8
Online ISBN: 978-3-319-70145-5
eBook Packages: Computer ScienceComputer Science (R0)