The Interestingness of Images

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

[1]  Craig A. Smith,et al.  Patterns of cognitive appraisal in emotion. , 1985, Journal of personality and social psychology.

[2]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1991, CACM.

[3]  P. Valdez,et al.  Effects of color on emotions. , 1994, Journal of experimental psychology. General.

[4]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[6]  A. Chen,et al.  An examination of situational interest and its sources. , 2001, The British journal of educational psychology.

[7]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[8]  Michal Irani,et al.  Detecting Irregularities in Images and in Video , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[9]  P. Silvia,et al.  Must interesting things be pleasant? A test of competing appraisal structures. , 2006, Emotion.

[10]  Yan Ke,et al.  The Design of High-Level Features for Photo Quality Assessment , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  James Ze Wang,et al.  Studying Aesthetics in Photographic Images Using a Computational Approach , 2006, ECCV.

[13]  Edward A. Vessel,et al.  Perceptual Pleasure and the Brain , 2006 .

[14]  P. Silvia.  Interest—The Curious Emotion , 2008 .

[15]  Antonio Torralba,et al.  How many pixels make an image? , 2009, Visual Neuroscience.

[16]  Allan Hanbury,et al.  Affective image classification using features inspired by psychology and art theory , 2010, ACM Multimedia.

[17]  Edward A. Vessel,et al.  Beauty and the beholder: highly individual taste for abstract, but not real-world images. , 2010, Journal of vision.

[18]  Svetlana Lazebnik,et al.  Superparsing , 2010, International Journal of Computer Vision.

[19]  Antonio Torralba,et al.  Understanding the Intrinsic Memorability of Images , 2011, NIPS.

[20]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[21]  Vicente Ordonez,et al.  High level describable attributes for predicting aesthetics and interestingness , 2011, CVPR 2011.

[22]  Tom Schaul,et al.  Coherence Progress: A Measure of Interestingness Based on Fixed Compressors , 2011, AGI.

[23]  Jianxiong Xiao,et al.  What makes an image memorable , 2011 .

[24]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  L. Gool,et al.  Visual Interestingness in Webcam-Streams , 2013 .

[26]  Luc Van Gool,et al.  Visual interestingness in image sequences , 2013, MM '13.

[27]  D. Berlyne.  Conflict, arousal, and curiosity , 2014 .