The Interestingness of Images

By Michael Gygli, Helmut Grabner, Hayko Riemenschneider, Fabian Nater, Luc Van Gool. 2013

203 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognizing Image Style (2013, background): “[10] gathered and predicted human evaluation of image interestingness, building on work by Isola et al.”
Salient object detection: A survey (2014, background): “Some topics that are closely or remotely related to visual saliency include: salient object detection [41], fixation prediction [33, 34], object importance [17, 157, 182], memorability [78], scene clutter [169], video interestingness [50, 69, 90, 96], surprise [80], image quality assessment [208, 20”
Summarization of Egocentric Videos: A Comprehensive Survey (2017, background): “3) Considering Only Importance to Convey Skims: User studies suggest that static images’ interestingness is related to factors such as saliency, edges and colorfulness, object interactions, and the presence of landmarks, people, or faces [47].”
Group MAD Competition? A New Methodology to Compare Objective Image Quality Models (2016, background): “To give a few examples, these may include comparisons of image/video interestingness predictors in the field of cognitive vision [8], the relative attributes (sportiness, furriness) estimators in the field of sematic image search [11], machine translation quality estimators in the field of computati”
Creating Summaries from User Videos (2014, methodology): “We compute an interestingness score ik for each frame vk, as a weighted sum of features that have been found to be related to interestingness [11,18].”
What makes an image popular? (2014, background): “Recent work has also analyzed the more general attribute of image intrestingness [53], particularly focusing on its correlation with image memorability [19].”
TVSum: Summarizing web videos using titles (2015, background): “Much work has been devoted to unsupervised video summarization, assessing the importance of frames using visual attention [16, 5], interestingness [21, 20], user engagement [33, 35], content frequency [52] and nonredundancy [30, 50].”
The Synthesizability of Texture Examples (2014, background): “Even if challenging, the task may be doable, given that other qualitative image characteristics could be quantified, like quality [26], memorability [14], or interestingness [11].”
Interestingness Prediction by Robust Learning to Rank (2014, methodology): “The performance of Huber-LASSO is also better than Jiang et al. [21] and Gygli et al. suggesting even a weaker global outlier detection approach is better then the majority voting based local one.”