High level describable attributes for predicting aesthetics and interestingness

Dhar, Sagnik; Ordóñez, Vicente; Berg, Tamara L.

doi:10.1109/cvpr.2011.5995467

Cited by 415 publications

(349 citation statements)

References 23 publications

(14 reference statements)

Supporting

Mentioning

331

Contrasting

Unclassified

Order By: Relevance

“…In a broader sense of attributes [26,11,12,27,13] interestingness can be considered as one type of relative attributes [35], although those attributes, such as how smiling a person is, are much less subjective. Computational models of interestingness Most earlier work casts the aesthetics or interestingness prediction problem as a regression problem [22,7,19,28]. However, as discussed before, obtaining an absolute value of interestingness for each data point is too subjective and affected too much by unknown personal preference/social background to be reliable.…”

Section: Related Workmentioning

confidence: 99%

“…Predicting image and video interestingness Early efforts on image interestingness prediction focus on different aspects than interestingness as such, including image quality [22], memorability [19], and aesthetics [7]. These properties are related to interestingness but different.…”

Section: Related Workmentioning

confidence: 99%

“…The problem of automatically predicting if people would find an image or video interesting has started to receive increasing attention [7,16,21]. Interestingness prediction has a number of real-world applications.…”

Section: Introductionmentioning

confidence: 99%

“…First, what defines interestingness and what cues contribute to the human perception of interestingness are still under investigation in psychophysics [39], cognitive sciences [4] and recently computer vision [7,16,21]. Therefore current research in computer vision on interestingness is primarily focused on designing relevant feature representations.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Interestingness Prediction by Robust Learning to Rank

Hospedales

Xiang

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. The problem of predicting image or video interestingness from their low-level feature representations has received increasing interest. As a highly subjective visual attribute, annotating the interestingness value of training data for learning a prediction model is challenging. To make the annotation less subjective and more reliable, recent studies employ crowdsourcing tools to collect pairwise comparisons -relying on majority voting to prune the annotation outliers/errors. In this paper, we propose a more principled way to identify annotation outliers by formulating the interestingness prediction task as a unified robust learning to rank problem, tackling both the outlier detection and interestingness prediction tasks jointly. Extensive experiments on both image and video interestingness benchmark datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interestingness Prediction by Robust Learning to Rank

Hospedales

Xiang

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

show abstract

“…This work was refined by Luo et al [5] by improving existing features with a variety of subject detection algorithms, such as super-pixel segmentation, layout and human detection. Dhar et al [6] introduced a high-level attributes layer to make the subject-based framework more integrated. Those works tended to use more high-complexity and describable features to imitate the photography rules.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Photographing Interface with On-Device Aesthetic Quality Assessment

Liu

Chen

2013

Computer Vision - ACCV 2012 Workshops

View full text Add to dashboard Cite

Abstract. This paper proposes a efficient method for instant photo aesthetics quality assessment that can be implemented on general portable devices. The classification performance is guaranteed to 0.89 on benchmark photo database. We also port our method onto a middle-level tablet computer to execute instantly and we find it reaches good acceptable efficiency. Moreover, an aesthetic information display to present the aesthetics evaluation results to users is introduced.

show abstract

Predicting the Personal Appeal of Marketing Images Using Computational Methods

Matz¹,

Segalin

Stillwell

et al. 2019

J Consum Psychol

View full text Add to dashboard Cite

Images play a central role in digital marketing. They attract attention, trigger emotions, and shape consumers' first impressions of products and brands. We propose that the shift from one-to-many mass communication to highly personalized one-to-one communication requires an understanding of image appeal at a personal level. Instead of asking "How appealing is this image?" we ask "How appealing is this image to this particular consumer?" Using the well-established five-factor model of personality, we apply machine learning algorithms to predict an image's personality appeal-the personality of consumers to which the image appeals most-from a set of 89 automatically extracted image features (Study 1). We subsequently apply the same algorithm on new images to predict consequential outcomes from the fit between consumer and image personality. We show that image-person fit adds incremental predictive power over the images' general appeal when predicting (a) consumers' liking of new images (Study 2) and (b) consumers' attitudes and purchase intentions (Study 3).

show abstract

High level describable attributes for predicting aesthetics and interestingness

Cited by 415 publications

References 23 publications

Interestingness Prediction by Robust Learning to Rank

Interestingness Prediction by Robust Learning to Rank

Intelligent Photographing Interface with On-Device Aesthetic Quality Assessment

Predicting the Personal Appeal of Marketing Images Using Computational Methods

Contact Info

Product

Resources

About