cvpr cvpr2013 cvpr2013-310 cvpr2013-310-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Babak Saleh, Ali Farhadi, Ahmed Elgammal
Abstract: When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting. We argue that abnormalities and deviations from typicalities are among the most important components that form what is worth mentioning. In this paper we introduce the abnormality detection as a recognition problem and show how to model typicalities and, consequently, meaningful deviations from prototypical properties of categories. Our model can recognize abnormalities and report the main reasons of any recognized abnormality. We also show that abnormality predictions can help image categorization. We introduce the abnormality detection dataset and show interesting results on how to reason about abnormalities.
[1] Lawrence W. Barsalou. Ideals, central tendency, and frequency of instantiation as determinants of graded strcture in categories. J. Experimental Psychology: Learning, Memory, and Cognition, 11(4):629–649, 1985.
[2] Oren Boiman and Michal Irani. Detecting irregularities in images and in video. International Journal of Computer Vision, 2007.
[3] Varun Chandola, Arindam Banerjee, and Vipin Kumar. Anomaly detection: A survey. ACM Comput. Surv.
[4] K. Grauman D. Parikh. Relative attributes. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, 2011.
[5] Mark Everingham, Luc Van Gool, C. K. I. Williams, J. Winn, and Andrew Zisserman. The pascal visual object classes (VOC) challenge. International Journal of Computer Vision (IJCV), 2010.
[6] A. Farhadi, I. Endres, and D. Hoiem. Attribute-centric recognition for cross-category generalization. 2010.
[7] A. Farhadi, I. Endres, D. Hoiem, and D. A. Forsyth. Describing objects by their attributes. 2009.
[8] A. Farhadi, S. Hejrati, A. Sadeghi, P. Young, C. Rashtchian, J. Hockenmaier, and D. Forsyth. Every picture tells a story: Generating sentences from images. 2010.
[9] J. Feldman. Bias toward regular form in mental shape spaces. Journal of Experimental Psychology: Human Perception & Performance, 26(1): 1–14, 2000.
[10] Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2010.
[11] Ann E.; Samuelson Larissa K.; Trejo Erika; Worzalla Samantha L.; Peltan Jessica R.; Oakes Lisa M. Horst, Jessica S.; Ellis. Developmental Science, v12.
[12] Phillip Isola, Devi Parikh, Antonio Torralba, and Aude Oliva. Understanding the intrinsic memorability of images. In Advances in Neural Information Processing Systems, 2011.
[13] Laurent Itti and Christof Koch. A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research, 40: 1489–1506, 2000.
[14] Yuri Ivanov, Aaron Bobick, Y. A. Ivanov, and A. F. Bobick. Recognition of multi-agent interaction in video surveillance. In In ICCV, pages 169–176, 1999.
[15] Tilke Judd, Krista Ehinger, Fr´ edo Durand, and Antonio Torralba. Learning to predict where humans look. In IEEE International Conference on Computer Vision (ICCV), 2009.
[16] Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, and Shree K. Nayar. Attribute and simile classifiers for face verification. In ICCV, 2009.
[17] Christoph H. Lampert, Hannes Nickisch, and Stefan Harmeling. Learning to detect unseen object classes by betweenclass attribute transfer. 2009.
[18] J. Liu, B. Kuipers, and S. Savarese. Recognizing human actions by attributes. In CVPR, 2011.
[19] Plunkett K. Mather E. Cognition.
[20] Mark T. Keane Michael W. Eysenck. Cognitive psychology: a student’s handbook. Psychology press, 2005.
[21] G. L. Murphy. The Big Book of Concepts (Bradford Books). The MIT Press, March 2002.
[22] Alan S. Willsky Myung Jin Choi, Antonio Torralba. Context models and out-of-context objects. In To appear in Pattern Recognition Letters, 2012.
[23] R.M. Nosofsky. Exemplar-based accounts of relations between classification, recognition, and typicality. Journal of
[24]
[25]
[26]
[27]
[28]
[29]
[30] [3 1]
[32]
[33]
[34] Experimental Psychology: Learning, Memory, and Cognition, 14(4):700–708, 1988. Sangdon Park, Wonsik Kim, and Kyoung Mu Lee. Abnormal object detection by canonical scene-based contextual model. In European Conference on Computer Vision (ECCV), 2012. Mohammad Rastegari, Ali Farhadi, and David Forsyth. Attribute discovery via predictable discriminative binary codes. In ECCV, 2012. Eleanor H. Rosch and Carolyn Mervis. Family resemblances: studies in the internal structure of cateogies. Cognitive Psychology, 7:573–605, 1975. Simpson .C Rosch E. and R. Scott Miller. Structural bases of typicality effects. Journal of Experimental Psychology: Human Perception and Performance, pages 491–502, 1976. Philippe G. Schyns, Robert L. Goldstone, and Jean-Pierre Thibaut. The development of features in object concepts. Behavioral and brain Sciences, 21:1–54, 1998. Chris Stauffer, W. Eric, and W. Eric L. Grimson. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000. J. B. Tenenbaum. Making sense of typicality: what makes a good example? In Nineteenth Annual Conference of the Cognitive Science Society, 1997. Antonio Torralba. Contextual Influences on Saliency, pages 586–593. Academic Press / Elsevier, 2005. Antonio Torralba, Kevin P. Murphy, William T. Freeman, and Mark A. Rubin. Context-based vision system for place and object recognition. 2003. Daphna Weinshall, Hynek Hermansky, Alon Zweig, Jie Luo, Holly Jimison, Frank Ohl, and Misha Pavel. Beyond novelty detection: Incongruent events, when general and specific classifiers disagree. 2008. J. Wilder, J. Feldman, and M. Singh. Superordinate shape classification using natural shape statistics. Cognition.
[35] H. Zhong, J. Shi, and M. Visontai. Detecting unusual activity in video. In Proc. Computer Society Conference on Computer Vision and Pattern Recognition (CVPR ’04), volume 2, 2004. 777779999944222