iccv iccv2013 iccv2013-416 iccv2013-416-reference knowledge-graph by maker-knowledge-mining

416 iccv-2013-The Interestingness of Images


Source: pdf

Author: Michael Gygli, Helmut Grabner, Hayko Riemenschneider, Fabian Nater, Luc Van_Gool

Abstract: We investigate human interest in photos. Based on our own and others ’psychological experiments, we identify various cues for “interestingness ”, namely aesthetics, unusualness and general preferences. For the ranking of retrieved images, interestingness is more appropriate than cues proposed earlier. Interestingness is, for example, correlated with what people believe they will remember. This is opposed to actual memorability, which is uncorrelated to both of them. We introduce a set of features computationally capturing the three main aspects of visual interestingness that we propose and build an interestingness predictor from them. Its performance is shown on three datasets with varying context, reflecting diverse levels of prior knowledge of the viewers.


reference text

[1] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk. SLIC superpixels compared to state-of-the-art superpixel methods. PAMI, 2012.

[2] D. Berlyne. Conflict, arousal, and curiosity. McGraw-Hill, 1960.

[3] I. Biederman and E. Vessel. Perceptual Pleasure and the Brain. American Scientist, 2006.

[4] O. Boiman and M. Irani. Detecting irregularities in images and in video. In ICCV, 2005.

[5] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. PAMI, 2001. portance of unusualness features decreases, as the context becomes weak.

[6] M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander. LOF: identifying density-based local outliers. In ACM Sigmod, 2000.

[7] D. S. Butterfield, C. Fake, C. J. Henderson-Begg, and S. Mourachov. Interestingness ranking of media objects, patent application 20060242139.

[8] C. Chang and C. Lin. LIBSVM: A library for support vector machines. ACM TIST, 2011.

[9] A. Chen, P. Darst, and R. Pangrazi. An examination of situational interest and its sources. Brit. J. of Edu. Psychology, 2001.

[10] R. Datta, D. Joshi, J. Li, and J. Z. Wang. Studying aesthetics in photographic images using a computational approach. In ECCV. 2006.

[11] S. Dhar, V. Ordonez, and T. L. Berg. High level describable attributes for predicting aesthetics and interestingness. In CVPR, 2011.

[12] H. Grabner, F. Nater, M. Druey, and L. Van Gool. Visual interestingness in Webcam-Streams. ACM MM, 2013.

[13] P. Isola, D. Parikh, A. Torralba, and A. Oliva. Understanding the intrinsic memorability of images. J. of Vision, 2012.

[14] P. Isola, J. Xiao, A. Torralba, and A. Oliva. What makes an image memorable? In CVPR, 2011.

[15] Y. Ke, X. Tang, and F. Jing. The design of high-level features for photo quality assessment. In CVPR, 2006.

[16] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, 2006.

[17] J. Machajdik and A. Hanbury. Affective image classification using features inspired by psychology and art theory. ACM MM, 2010.

[18] A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 2001.

[19] T. Schaul, L. Pape, T. Glasmachers, V. Graziano, and J. Schmidhuber. Coherence progress: A measure of interestingness based on fixed compressors. In AGI, 2011.

[20] P. J. Silvia. Interest - The Curious Emotion. CDPS, 2008.

[21] C. A. Smith and P. C. Ellsworth. Patterns of cognitive appraisal in emotion. J. of of Personality and Social Psychology, 1985.

[22] J. Tighe and S. Lazebnik. Superparsing: scalable nonparametric image parsing with superpixels. In ECCV. 2010.

[23] A. Torralba. How many pixels make an image. Visual neuroscience, 2009.

[24] S. A. Turner Jr and P. J. Silvia. Must interesting things be pleasant? A test of competing appraisal structures. Emotion, 2006.

[25] P. Valdez and A. Mehrabian. Effects of color on emotions. J. of Experimental Psychology, 1994.

[26] E. A. Vessel and N. Rubin. Beauty and the beholder : Highly individual taste for abstract , but not real-world images. J. of Vision, 2010.

[27] G. K. Wallace. The JPEG still picture compression standard. Comm. of the ACM, 1991. 11664400