Abstract
Finding recurring visual patterns in data underlies much of modern computer vision. The emerging subfield of visual category discovery/visual data mining proposes to cluster visual patterns that capture more complex appearance than low-level blobs, corners, or oriented bars, without requiring any semantic labels. In particular, mid-level visual elements have recently been proposed as a new type of visual primitive, and have been shown to be useful for various recognition tasks. The visual elements are discovered automatically from the data, and thus, have a flexible representation of being either a part, an object, a group of objects, etc. In this chapter, we explore what the mid-level visual representation brings to geo-spatial and longitudinal analyses. Specifically, we present a weakly supervised visual data mining approach that discovers connections between recurring mid-level visual elements in historic (temporal) and geographic (spatial) image collections, and attempts to capture the underlying visual style. In contrast to existing discovery methods that mine for patterns that remain visually consistent throughout the dataset, the goal is to discover visual elements whose appearance changes due to change in time or location, i.e., exhibit consistent stylistic variations across the label space (date or geo-location). To discover these elements, we first identify groups of patches that are style-sensitive. We then incrementally build correspondences to find the same element across the entire dataset. Finally, we train style-aware regressors that model each element’s range of stylistic differences. We apply our approach to date and geo-location prediction and show substantial improvement over several baselines that do not model visual style. We also demonstrate the method’s effectiveness on the related task of fine-grained classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berg T, Belhumeur P (2013) POOF: part-based one-vs-one features for fine-grained categorization, face verification, and attribute estimation. In: CVPR
Chai Y, Lempitsky V, Zisserman A (2013) Symbiotic segmentation and part localization for fine-grained categorization. In: ICCV
Chen CY, Grauman K (2011) Clues from the beaten path: location estimation with bursty sequences of tourist photos. In: CVPR
Cristani M, Perina A, Castellani U, Murino V (2008) Geolocated image analysis using latent representations. In: CVPR
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR
Doersch C, Singh S, Gupta A, Sivic J, Efros AA (2012) What makes Paris look like Paris? In: SIGGRAPH
Duan K, Parikh D, Crandall D, Grauman K (2012) Discovering localized attributes for fine-grained recognition. In: CVPR
Faktor A, Irani M (2012) Clustering by composition unsupervised discovery of image categories. In: ECCV
Farrell R, Oza O, Zhang N, Morariu V, Darrell T, Davis L (2011) Birdlets: subordinate categorization using volumetric primitives and pose-normalized appearance. In: ICCV
Fu Y, Guo G-D, Huang T (2010) Age synthesis and estimation via faces: a survey. TPAMI
Gavves E, Fernando B, Snoek C, Smeulders A, Tuytelaars T (2013) Fine-grained categorization by alignments. In: ICCV
Grauman K, Darrell T (2006) Unsupervised learning of categories from sets of partially matching image features. In: CVPR
Hays J, Efros A (2008) Im2gps: estimating geographic information from a single image. In: CVPR
Kalogerakis E, Vesselova O, Hays J, Efros A, Hertzmann A (2009) Image sequence geolocation with human travel priors. In: ICCV
Kim G, Xing E, Torralba A (2010) Modeling and analysis of dynamic behaviors of web image collections. In: ECCV
Knopp J, Sivic J, Pajdla T (2010) Avoiding confusing features in place recognition. In: ECCV
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR
Lee YJ, Efros AA, Hebert M (2013) Style-aware mid-level representation for discovering visual connections in space and time. In: ICCV
Lee YJ, Grauman K (2009) Foreground focus: unsupervised learning from partially matching images. In: IJCV, vol 85
Lee YJ, Grauman K (2011) Object-graphs for context-aware visual category discovery. In: TPAMI
Li L-J, Su H, Xing E, Fei-Fei L (2010) Object bank: a high-level image representation for scene classification and semantic feature sparsification. In: NIPS
Malisiewicz T, Efros A (2009) Beyond categories: the visual memex model for reasoning about object relationships. In: NIPS
Palermo F, Hays J, Efros AA (2012) Dating historical color images. In: ECCV
Parikh D, Grauman K (2011) Relative attributes. In: ICCV
Payet N, Todorovic S (2010) From a set of shapes to object discovery. In: ECCV
Raptis M, Kokkinos I, Soatto S (2012) Discovering discriminative action parts from mid-level video representations. In: CVPR
Rastegariy M, Farhadi A, Forsyth D (2012) Attribute discovery via predictable discriminative binary codes. In: ECCV
Schindler G, Brown M, Szeliski R (2007) Cityscale location recognition. In CVPR
Shrivastava A, Singh S, Gupta A (2012) Constrained semi-supervised learning using attributes and comparative attributes. In: ECCV
Singh S, Gupta A, Efros AA (2012) Unsupervised discovery of mid-level discriminative patches. In: ECCV
Sivic J, Russell B, Efros A, Zisserman A, Freeman W (2005) Discovering object categories in image collections. In: ICCV
Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. In: ICCV
Smola A, Schlkopf B (2003) A tutorial on support vector regression. Technical report, Statistics and Computing
Tenenbaum J, Freeman W (2000) Separating style and content with bilinear models. Neural Comput 12(6)
Torralba A, Efros AA (2011) Unbiased look at dataset bias. In: CVPR
Wah C, Branson S, Perona P, Belongie S (2011) Multiclass recognition part localization with humans in the loop. In: ICCV
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-UCSD birds-200-2011 dataset. Technical report
Yang S, Bo L, Wang J, Shapiro L (2012) Unsupervised template learning for fine-grained object recognition. In: NIPS
Yao B, Khosla A, Fei-Fei L (2011) Combining randomization and discrimination for fine-grained image categorization. In: CVPR
Zhang N, Farrell R, Darrell T (2012) Pose pooling kernels for sub-category recognition. In: CVPR
Zhang N, Farrell R, Iandola F, Darrell T (2013) Deformable part descriptors for fine-grained recognition and attribute prediction. In: ICCV
Acknowledgments
We thank Olivier Duchenne for helpful discussions. This work was supported in part by Google, ONR MURI N000141010934, and the Intelligence Advanced Research Projects Activity (IARPA) via Air Force Research Laboratory. The U.S. government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, AFRL or the U.S. government.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Lee, Y.J., Efros, A.A., Hebert, M. (2016). Discovering Mid-level Visual Connections in Space and Time. In: Zamir, A., Hakeem, A., Van Gool, L., Shah, M., Szeliski, R. (eds) Large-Scale Visual Geo-Localization. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-25781-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-25781-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25779-2
Online ISBN: 978-3-319-25781-5
eBook Packages: Computer ScienceComputer Science (R0)